More

src/gpu/mod.rs

@@ -463,6 +463,8 @@ pub mod shaders {
     pub const EQUIRECT_TO_CUBEMAP: &str = include_str!("shaders/equirect_to_cubemap.wgsl");
     /// Downscale + grayscale + Laplacian variance (sharpness scoring).
     pub const SHARPNESS: &str = include_str!("shaders/sharpness.wgsl");
+    /// Downscale to a tiny luma thumbnail (motion/parallax proxy).
+    pub const THUMBNAIL: &str = include_str!("shaders/thumbnail.wgsl");
     /// Cubemap -> equirect (nearest, for mask reprojection).
     pub const C2E: &str = include_str!("shaders/c2e.wgsl");
 }

src/gpu/shaders/thumbnail.wgsl

@@ -0,0 +1,36 @@
+// Stage-1 companion kernel: build a tiny grayscale luma thumbnail on the GPU.
+//
+// One thread per thumbnail pixel. Each thread nearest-samples a source pixel
+// and writes its luma (0..255) into `thumb[ty * tw + tx]`. This lets the motion
+// (parallax) proxy be computed on the GPU instead of the CPU reading the full
+// RGBA frame, so extraction leans on the GPU rather than the CPU.
+
+struct Params {
+    w: u32,
+    h: u32,
+    tw: u32,
+    th: u32,
+    pad0: u32,
+}
+
+@group(0) @binding(0) var<uniform> params: Params;
+@group(0) @binding(1) var src_tex: texture_2d<f32>;
+@group(0) @binding(2) var<storage, read_write> thumb: array<f32>;
+
+fn luma(c: vec4<f32>) -> f32 {
+    return 0.299 * c.r + 0.587 * c.g + 0.114 * c.b;
+}
+
+@compute @workgroup_size(256, 1, 1)
+fn main(@builtin(global_invocation_id) gid: vec3<u32>) {
+    let i = gid.x;
+    if (i >= params.tw * params.th) {
+        return;
+    }
+    let tx = i % params.tw;
+    let ty = i / params.tw;
+    let sx = i32(tx * params.w / params.tw);
+    let sy = i32(ty * params.h / params.th);
+    // Scale to 0..255 to match the CPU thumbnail / motion-diff convention.
+    thumb[i] = luma(textureLoad(src_tex, vec2<i32>(sx, sy), 0)) * 255.0;
+}

src/gui.rs

@@ -68,16 +68,18 @@ struct RunHandle {
 
 impl RunHandle {
     fn spawn(mut cmd: std::process::Command) -> std::io::Result<RunHandle> {
-        let mut child = cmd
+        let mut child = cmd.stdout(Stdio::piped()).stderr(Stdio::piped()).spawn()?;
-            .stdout(Stdio::piped())
-            .stderr(Stdio::piped())
-            .spawn()?;
         let stdout = child.stdout.take().unwrap();
         let stderr = child.stderr.take().unwrap();
         let (tx, rx) = mpsc::channel::<Line>();
         spawn_line_reader(stdout, tx.clone(), false);
         spawn_line_reader(stderr, tx, true);
-        Ok(RunHandle { child, rx, started: Instant::now(), code: None })
+        Ok(RunHandle {
+            child,
+            rx,
+            started: Instant::now(),
+            code: None,
+        })
     }
 
     fn poll(&mut self, log: &mut VecDeque<String>) {
@@ -110,7 +112,11 @@ impl RunHandle {
     }
 }
 
-fn spawn_line_reader<R: std::io::Read + Send + 'static>(mut r: R, tx: Sender<Line>, is_stderr: bool) {
+fn spawn_line_reader<R: std::io::Read + Send + 'static>(
+    mut r: R,
+    tx: Sender<Line>,
+    is_stderr: bool,
+) {
     std::thread::spawn(move || {
         let mut buf = [0u8; 8192];
         let mut leftover = Vec::new();
@@ -167,10 +173,22 @@ struct ExtractForm {
 impl Default for ExtractForm {
     fn default() -> Self {
         Self {
-            chunk_size: 30, scale_width: 1920, output_format: "png".into(), jpeg_quality: 95,
+            chunk_size: 30,
-            min_sharpness: 0.0, min_exposure: 0.0, max_exposure: 255.0, min_contrast: 0.0,
+            scale_width: 1920,
-            min_motion: 0.0, max_motion: 1.0e12, selection: "chunk".into(), target_count: 0,
+            output_format: "png".into(),
-            min_gap: 0, bad_frame_action: "keep".into(), motion_mode: "frame_diff".into(), batch: 8,
+            jpeg_quality: 95,
+            min_sharpness: 0.0,
+            min_exposure: 0.0,
+            max_exposure: 255.0,
+            min_contrast: 0.0,
+            min_motion: 0.0,
+            max_motion: 1.0e12,
+            selection: "chunk".into(),
+            target_count: 0,
+            min_gap: 0,
+            bad_frame_action: "keep".into(),
+            motion_mode: "frame_diff".into(),
+            batch: 8,
         }
     }
 }
@@ -183,35 +201,65 @@ struct MasksForm {
     conf: f64,
     imgsz: u32,
     dilate: u32,
-    projection: String,
-    face_size: u32,
     skip_faces: String,
-    tile_batch: u32,
+    batch: u32,
     empty_if_none: bool,
     iou: f64,
+    // MIGraphX compiled-model cache directory (optional override; defaults to
+    // ~/.cache/pipeline_360/migraphx when unset).
+    ep_cache: Option<PathBuf>,
 }
 
 impl Default for MasksForm {
     fn default() -> Self {
         Self {
             classes: "person,car,bus,truck,bicycle,motorcycle".into(),
-            model: PathBuf::from("yolo11x-seg.onnx"), device: "cpu".into(), conf: 0.35,
+            model: PathBuf::from("yolo11x-seg.onnx"),
-            imgsz: 1280, dilate: 6, projection: "cubemap".into(), face_size: 1024,
+            device: "cpu".into(),
-            skip_faces: String::new(), tile_batch: 8, empty_if_none: false, iou: 0.45,
+            conf: 0.35,
+            imgsz: 1280,
+            dilate: 6,
+            skip_faces: String::new(),
+            batch: 8,
+            empty_if_none: false,
+            iou: 0.45,
+            ep_cache: None,
         }
     }
 }
 
 #[derive(Clone)]
-struct CubemapForm { face_size: u32, skip_faces: String, jpeg_quality: u32, batch: u32 }
+struct CubemapForm {
+    face_size: u32,
+    skip_faces: String,
+    jpeg_quality: u32,
+    batch: u32,
+}
 impl Default for CubemapForm {
-    fn default() -> Self { Self { face_size: 1600, skip_faces: "U,D".into(), jpeg_quality: 95, batch: 4 } }
+    fn default() -> Self {
+        Self {
+            face_size: 1600,
+            skip_faces: "U,D".into(),
+            jpeg_quality: 95,
+            batch: 4,
+        }
+    }
 }
 
 #[derive(Clone)]
-struct RigForm { ref_face: String, intrinsics_convention: String, link_mode: String }
+struct RigForm {
+    ref_face: String,
+    intrinsics_convention: String,
+    link_mode: String,
+}
 impl Default for RigForm {
-    fn default() -> Self { Self { ref_face: "F".into(), intrinsics_convention: "linspace".into(), link_mode: "symlink".into() } }
+    fn default() -> Self {
+        Self {
+            ref_face: "F".into(),
+            intrinsics_convention: "linspace".into(),
+            link_mode: "symlink".into(),
+        }
+    }
 }
 
 // ---------------------------------------------------------------------------
@@ -239,11 +287,23 @@ impl Default for App {
     fn default() -> Self {
         let cli = resolve_cli_binary();
         Self {
-            project_dir: PathBuf::new(), videos: Vec::new(), start_stage: "extract".into(),
+            project_dir: PathBuf::new(),
-            skip_masks: false, extract: ExtractForm::default(), masks: MasksForm::default(),
+            videos: Vec::new(),
-            cubemap: CubemapForm::default(), rig: RigForm::default(),
+            start_stage: "extract".into(),
-            cli_binary_str: cli.as_ref().map(|p| p.display().to_string()).unwrap_or_else(|| "pipeline_360 (NOT FOUND — build it first)".into()),
+            skip_masks: false,
-            cli_binary: cli, log: VecDeque::new(), run: None, status: "Idle".into(), last_progress: String::new(),
+            extract: ExtractForm::default(),
+            masks: MasksForm::default(),
+            cubemap: CubemapForm::default(),
+            rig: RigForm::default(),
+            cli_binary_str: cli
+                .as_ref()
+                .map(|p| p.display().to_string())
+                .unwrap_or_else(|| "pipeline_360 (NOT FOUND — build it first)".into()),
+            cli_binary: cli,
+            log: VecDeque::new(),
+            run: None,
+            status: "Idle".into(),
+            last_progress: String::new(),
         }
     }
 }
@@ -269,55 +329,88 @@ impl App {
 
         let e = &self.extract;
         cmd.args([
-            "--extract-chunk-size", &e.chunk_size.to_string(),
+            "--extract-chunk-size",
-            "--extract-scale-width", &e.scale_width.to_string(),
+            &e.chunk_size.to_string(),
-            "--extract-output-format", &e.output_format,
+            "--extract-scale-width",
-            "--extract-jpeg-quality", &e.jpeg_quality.to_string(),
+            &e.scale_width.to_string(),
-            "--extract-min-sharpness", &fmt_f(e.min_sharpness),
+            "--extract-output-format",
-            "--extract-min-exposure", &fmt_f(e.min_exposure),
+            &e.output_format,
-            "--extract-max-exposure", &fmt_f(e.max_exposure),
+            "--extract-jpeg-quality",
-            "--extract-min-contrast", &fmt_f(e.min_contrast),
+            &e.jpeg_quality.to_string(),
-            "--extract-min-motion", &fmt_f(e.min_motion),
+            "--extract-min-sharpness",
-            "--extract-max-motion", &fmt_f(e.max_motion),
+            &fmt_f(e.min_sharpness),
-            "--extract-selection", &e.selection,
+            "--extract-min-exposure",
-            "--extract-target-count", &e.target_count.to_string(),
+            &fmt_f(e.min_exposure),
-            "--extract-min-gap", &e.min_gap.to_string(),
+            "--extract-max-exposure",
-            "--extract-bad-frame-action", &e.bad_frame_action,
+            &fmt_f(e.max_exposure),
-            "--extract-motion-mode", &e.motion_mode,
+            "--extract-min-contrast",
-            "--extract-batch", &e.batch.to_string(),
+            &fmt_f(e.min_contrast),
+            "--extract-min-motion",
+            &fmt_f(e.min_motion),
+            "--extract-max-motion",
+            &fmt_f(e.max_motion),
+            "--extract-selection",
+            &e.selection,
+            "--extract-target-count",
+            &e.target_count.to_string(),
+            "--extract-min-gap",
+            &e.min_gap.to_string(),
+            "--extract-bad-frame-action",
+            &e.bad_frame_action,
+            "--extract-motion-mode",
+            &e.motion_mode,
+            "--extract-batch",
+            &e.batch.to_string(),
         ]);
 
         let m = &self.masks;
         cmd.args([
-            "--mask-classes", &m.classes,
+            "--mask-classes",
-            "--mask-model", &m.model.display().to_string(),
+            &m.classes,
-            "--mask-device", &m.device,
+            "--mask-model",
-            "--mask-conf", &fmt_f(m.conf),
+            &m.model.display().to_string(),
-            "--mask-imgsz", &m.imgsz.to_string(),
+            "--mask-device",
-            "--mask-dilate", &m.dilate.to_string(),
+            &m.device,
-            "--mask-projection", &m.projection,
+            "--mask-conf",
-            "--mask-face-size", &m.face_size.to_string(),
+            &fmt_f(m.conf),
-            "--mask-skip-faces", &m.skip_faces,
+            "--mask-imgsz",
-            "--mask-tile-batch", &m.tile_batch.to_string(),
+            &m.imgsz.to_string(),
-            "--mask-iou", &fmt_f(m.iou),
+            "--mask-dilate",
+            &m.dilate.to_string(),
+            "--mask-skip-faces",
+            &m.skip_faces,
+            "--mask-batch",
+            &m.batch.to_string(),
+            "--mask-iou",
+            &fmt_f(m.iou),
         ]);
         if m.empty_if_none {
             cmd.arg("--mask-empty-if-none");
         }
+        if let Some(cache) = &m.ep_cache {
+            cmd.arg("--mask-ep-cache").arg(cache);
+        }
 
         let c = &self.cubemap;
         cmd.args([
-            "--cubemap-face-size", &c.face_size.to_string(),
+            "--cubemap-face-size",
-            "--cubemap-skip-faces", &c.skip_faces,
+            &c.face_size.to_string(),
-            "--cubemap-jpeg-quality", &c.jpeg_quality.to_string(),
+            "--cubemap-skip-faces",
-            "--cubemap-batch", &c.batch.to_string(),
+            &c.skip_faces,
+            "--cubemap-jpeg-quality",
+            &c.jpeg_quality.to_string(),
+            "--cubemap-batch",
+            &c.batch.to_string(),
         ]);
 
         let r = &self.rig;
         cmd.args([
-            "--rig-ref-face", &r.ref_face,
+            "--rig-ref-face",
-            "--rig-intrinsics-convention", &r.intrinsics_convention,
+            &r.ref_face,
-            "--rig-link-mode", &r.link_mode,
+            "--rig-intrinsics-convention",
+            &r.intrinsics_convention,
+            "--rig-link-mode",
+            &r.link_mode,
         ]);
         Some(cmd)
     }
@@ -334,7 +427,9 @@ impl App {
             self.status = "Error: choose a project dir and at least one video.".into();
             return;
         }
-        let Some(cmd) = self.build_command() else { return };
+        let Some(cmd) = self.build_command() else {
+            return;
+        };
         self.log.clear();
         self.last_progress.clear();
         self.status = "Running…".into();
@@ -355,20 +450,33 @@ impl App {
 
 fn fmt_f(v: impl ToString) -> String {
     let s = v.to_string();
-    if s.eq_ignore_ascii_case("inf") { "1e12".into() } else { s }
+    if s.eq_ignore_ascii_case("inf") {
+        "1e12".into()
+    } else {
+        s
+    }
 }
 
 fn cmd_to_string(cmd: &std::process::Command) -> String {
     let prog = cmd.get_program().to_string_lossy().to_string();
-    let args: Vec<String> = cmd.get_args().map(|a| {
+    let args: Vec<String> = cmd
+        .get_args()
+        .map(|a| {
             let a = a.to_string_lossy().to_string();
-        if a.contains(' ') { format!("\"{a}\"") } else { a }
+            if a.contains(' ') {
-    }).collect();
+                format!("\"{a}\"")
+            } else {
+                a
+            }
+        })
+        .collect();
     format!("{prog} {}", args.join(" "))
 }
 
 fn combo(ui: &mut egui::Ui, id: &str, options: &[&str], val: &mut String) {
-    egui::ComboBox::from_id_salt(id).selected_text(val.clone()).show_ui(ui, |ui| {
+    egui::ComboBox::from_id_salt(id)
+        .selected_text(val.clone())
+        .show_ui(ui, |ui| {
             for o in options {
                 ui.selectable_value(val, (*o).to_string(), *o);
             }
@@ -382,7 +490,11 @@ impl eframe::App for App {
             h.poll(&mut self.log);
             if let Some(code) = h.code {
                 if !self.status.starts_with("Cancelled") {
-                    self.status = if code == 0 { "Pipeline complete.".into() } else { format!("Pipeline exited with code {code}. See log.") };
+                    self.status = if code == 0 {
+                        "Pipeline complete.".into()
+                    } else {
+                        format!("Pipeline exited with code {code}. See log.")
+                    };
                 }
             }
         }
@@ -396,18 +508,28 @@ impl eframe::App for App {
                     let status = if self.is_running() {
                         if let Some(h) = self.run.as_ref() {
                             format!("{} ({}s)", self.status, h.elapsed().as_secs())
-                        } else { self.status.clone() }
+                        } else {
-                    } else { self.status.clone() };
+                            self.status.clone()
+                        }
+                    } else {
+                        self.status.clone()
+                    };
                     ui.label(egui::RichText::new(status).strong());
                     ui.with_layout(egui::Layout::right_to_left(egui::Align::Center), |ui| {
                         let running = self.is_running();
                         if running {
                             ui.spinner();
                         }
-                        if ui.add_enabled(running, egui::Button::new("⏹ Stop")).clicked() {
+                        if ui
+                            .add_enabled(running, egui::Button::new("⏹ Stop"))
+                            .clicked()
+                        {
                             self.cancel();
                         }
-                        if ui.add_enabled(!running, egui::Button::new("▶ Run pipeline")).clicked() {
+                        if ui
+                            .add_enabled(!running, egui::Button::new("▶ Run pipeline"))
+                            .clicked()
+                        {
                             self.start();
                         }
                     });
@@ -443,7 +565,11 @@ impl eframe::App for App {
                 egui::ScrollArea::vertical().show(ui, |ui| {
                     ui.heading("360° -> COLMAP cubemap rig");
                     ui.add_space(2.0);
-                    ui.label(egui::RichText::new(format!("CLI: {}", self.cli_binary_str)).small().color(egui::Color32::GRAY));
+                    ui.label(
+                        egui::RichText::new(format!("CLI: {}", self.cli_binary_str))
+                            .small()
+                            .color(egui::Color32::GRAY),
+                    );
 
                     ui.add_space(8.0);
                     ui.label("Project directory");
@@ -486,7 +612,7 @@ impl eframe::App for App {
                         egui::ComboBox::from_id_salt("start_stage")
                             .selected_text(self.start_stage.clone())
                             .show_ui(ui, |ui| {
-                                for s in ["extract", "masks", "cubemap", "rig"] {
+                                for s in ["extract", "cubemap", "masks", "rig"] {
                                     ui.selectable_value(&mut self.start_stage, s.into(), s);
                                 }
                             });
@@ -504,75 +630,239 @@ impl eframe::App for App {
                     .default_open(true)
                     .show(ui, |ui| {
                         let e = &mut self.extract;
-                        egui::Grid::new("extract_grid").num_columns(2).spacing([8.0, 4.0]).show(ui, |ui| {
+                        egui::Grid::new("extract_grid")
-                            ui.label("Chunk size");        ui.add(egui::DragValue::new(&mut e.chunk_size).range(1..=10000)); ui.end_row();
+                            .num_columns(2)
-                            ui.label("Scale width");       ui.add(egui::DragValue::new(&mut e.scale_width).range(0..=8000)); ui.end_row();
+                            .spacing([8.0, 4.0])
-                            ui.label("Output format");    combo(ui, "extract_fmt", &["png", "jpg"], &mut e.output_format); ui.end_row();
+                            .show(ui, |ui| {
-                            ui.label("JPEG quality");      ui.add(egui::DragValue::new(&mut e.jpeg_quality).range(1..=100)); ui.end_row();
+                                ui.label("Chunk size");
-                            ui.label("Batch (frames/GPU)");ui.add(egui::DragValue::new(&mut e.batch).range(1..=64)); ui.end_row();
+                                ui.add(egui::DragValue::new(&mut e.chunk_size).range(1..=10000));
-                            ui.label("Selection");         combo(ui, "extract_sel", &["chunk", "spread"], &mut e.selection); ui.end_row();
+                                ui.end_row();
-                            ui.label("Target count");     ui.add(egui::DragValue::new(&mut e.target_count).range(0..=100000)); ui.end_row();
+                                ui.label("Scale width");
-                            ui.label("Min gap (frames)");  ui.add(egui::DragValue::new(&mut e.min_gap).range(0..=10000)); ui.end_row();
+                                ui.add(egui::DragValue::new(&mut e.scale_width).range(0..=8000));
-                            ui.label("Bad-frame action");  combo(ui, "extract_bfa", &["keep", "skip", "warn"], &mut e.bad_frame_action); ui.end_row();
+                                ui.end_row();
-                            ui.label("Motion mode");      combo(ui, "extract_mm", &["frame_diff", "off"], &mut e.motion_mode); ui.end_row();
+                                ui.label("Output format");
+                                combo(ui, "extract_fmt", &["png", "jpg"], &mut e.output_format);
+                                ui.end_row();
+                                ui.label("JPEG quality");
+                                ui.add(egui::DragValue::new(&mut e.jpeg_quality).range(1..=100));
+                                ui.end_row();
+                                ui.label("Batch (frames/GPU)");
+                                ui.add(egui::DragValue::new(&mut e.batch).range(1..=64));
+                                ui.end_row();
+                                ui.label("Selection");
+                                combo(ui, "extract_sel", &["chunk", "spread"], &mut e.selection);
+                                ui.end_row();
+                                ui.label("Target count");
+                                ui.add(egui::DragValue::new(&mut e.target_count).range(0..=100000));
+                                ui.end_row();
+                                ui.label("Min gap (frames)");
+                                ui.add(egui::DragValue::new(&mut e.min_gap).range(0..=10000));
+                                ui.end_row();
+                                ui.label("Bad-frame action");
+                                combo(
+                                    ui,
+                                    "extract_bfa",
+                                    &["keep", "skip", "warn"],
+                                    &mut e.bad_frame_action,
+                                );
+                                ui.end_row();
+                                ui.label("Motion mode");
+                                combo(ui, "extract_mm", &["frame_diff", "off"], &mut e.motion_mode);
+                                ui.end_row();
                             });
-                        ui.label(egui::RichText::new("Quality thresholds (0/255 bounds = no filter):").small());
+                        ui.label(
+                            egui::RichText::new("Quality thresholds (0/255 bounds = no filter):")
+                                .small(),
+                        );
                         let e = &mut self.extract;
-                        egui::Grid::new("extract_q").num_columns(2).spacing([8.0, 4.0]).show(ui, |ui| {
+                        egui::Grid::new("extract_q")
-                            ui.label("Min sharpness"); ui.add(egui::DragValue::new(&mut e.min_sharpness).speed(0.05).range(0.0..=1.0e9)); ui.end_row();
+                            .num_columns(2)
-                            ui.label("Min exposure");  ui.add(egui::DragValue::new(&mut e.min_exposure).speed(1.0).range(0.0..=255.0)); ui.end_row();
+                            .spacing([8.0, 4.0])
-                            ui.label("Max exposure");  ui.add(egui::DragValue::new(&mut e.max_exposure).speed(1.0).range(0.0..=255.0)); ui.end_row();
+                            .show(ui, |ui| {
-                            ui.label("Min contrast");  ui.add(egui::DragValue::new(&mut e.min_contrast).speed(1.0).range(0.0..=255.0)); ui.end_row();
+                                ui.label("Min sharpness");
-                            ui.label("Min motion");    ui.add(egui::DragValue::new(&mut e.min_motion).speed(1.0).range(0.0..=255.0)); ui.end_row();
+                                ui.add(
-                            ui.label("Max motion");    ui.add(egui::DragValue::new(&mut e.max_motion).speed(1.0).range(0.0..=1.0e9)); ui.end_row();
+                                    egui::DragValue::new(&mut e.min_sharpness)
+                                        .speed(0.05)
+                                        .range(0.0..=1.0e9),
+                                );
+                                ui.end_row();
+                                ui.label("Min exposure");
+                                ui.add(
+                                    egui::DragValue::new(&mut e.min_exposure)
+                                        .speed(1.0)
+                                        .range(0.0..=255.0),
+                                );
+                                ui.end_row();
+                                ui.label("Max exposure");
+                                ui.add(
+                                    egui::DragValue::new(&mut e.max_exposure)
+                                        .speed(1.0)
+                                        .range(0.0..=255.0),
+                                );
+                                ui.end_row();
+                                ui.label("Min contrast");
+                                ui.add(
+                                    egui::DragValue::new(&mut e.min_contrast)
+                                        .speed(1.0)
+                                        .range(0.0..=255.0),
+                                );
+                                ui.end_row();
+                                ui.label("Min motion");
+                                ui.add(
+                                    egui::DragValue::new(&mut e.min_motion)
+                                        .speed(1.0)
+                                        .range(0.0..=255.0),
+                                );
+                                ui.end_row();
+                                ui.label("Max motion");
+                                ui.add(
+                                    egui::DragValue::new(&mut e.max_motion)
+                                        .speed(1.0)
+                                        .range(0.0..=1.0e9),
+                                );
+                                ui.end_row();
                             });
                     });
 
-                egui::CollapsingHeader::new("Stage 2 — Masks (YOLO segmentation; needs --features masks)")
+                egui::CollapsingHeader::new(
+                    "Stage 3 — Masks (YOLO segmentation; runs on cube faces)",
+                )
                 .show(ui, |ui| {
                     let m = &mut self.masks;
-                        egui::Grid::new("masks_grid").num_columns(2).spacing([8.0, 4.0]).show(ui, |ui| {
+                    egui::Grid::new("masks_grid")
-                            ui.label("Classes");      ui.text_edit_singleline(&mut m.classes); ui.end_row();
+                        .num_columns(2)
-                            ui.label("Model (ONNX)");  ui.horizontal(|ui| {
+                        .spacing([8.0, 4.0])
+                        .show(ui, |ui| {
+                            ui.label("Classes");
+                            ui.text_edit_singleline(&mut m.classes);
+                            ui.end_row();
+                            ui.label("Model (ONNX)");
+                            ui.horizontal(|ui| {
                                 let mut s = m.model.display().to_string();
                                 let r = ui.text_edit_singleline(&mut s);
-                                if r.changed() { m.model = PathBuf::from(s); }
+                                if r.changed() {
+                                    m.model = PathBuf::from(s);
+                                }
                                 if ui.button("…").clicked() {
-                                    if let Some(p) = rfd::FileDialog::new().add_filter("ONNX", &["onnx"]).pick_file() { m.model = p; }
+                                    if let Some(p) = rfd::FileDialog::new()
+                                        .add_filter("ONNX", &["onnx"])
+                                        .pick_file()
+                                    {
+                                        m.model = p;
+                                    }
                                 }
                             });
                             ui.end_row();
-                            ui.label("Device");       combo(ui, "mask_dev", &["cpu", "cuda", "rocm"], &mut m.device); ui.end_row();
+                            ui.label("Device");
-                            ui.label("Conf");         ui.add(egui::DragValue::new(&mut m.conf).speed(0.01).range(0.0..=1.0).fixed_decimals(2)); ui.end_row();
+                            combo(ui, "mask_dev", &["cpu", "rocm", "migraphx"], &mut m.device);
-                            ui.label("Imgsz");        ui.add(egui::DragValue::new(&mut m.imgsz).range(64..=4096)); ui.end_row();
+                            ui.end_row();
-                            ui.label("Dilate (px)");   ui.add(egui::DragValue::new(&mut m.dilate).range(0..=100)); ui.end_row();
+                            ui.label("Conf");
-                            ui.label("Projection");   combo(ui, "mask_proj", &["cubemap", "equirect"], &mut m.projection); ui.end_row();
+                            ui.add(
-                            ui.label("Face size");    ui.add(egui::DragValue::new(&mut m.face_size).range(64..=4096)); ui.end_row();
+                                egui::DragValue::new(&mut m.conf)
-                            ui.label("Skip faces");   ui.text_edit_singleline(&mut m.skip_faces); ui.end_row();
+                                    .speed(0.01)
-                            ui.label("Tile batch");   ui.add(egui::DragValue::new(&mut m.tile_batch).range(1..=64)); ui.end_row();
+                                    .range(0.0..=1.0)
-                            ui.label("NMS IoU");      ui.add(egui::DragValue::new(&mut m.iou).speed(0.01).range(0.0..=1.0).fixed_decimals(2)); ui.end_row();
+                                    .fixed_decimals(2),
+                            );
+                            ui.end_row();
+                            ui.label("Imgsz");
+                            ui.add(egui::DragValue::new(&mut m.imgsz).range(64..=4096));
+                            ui.end_row();
+                            ui.label("Dilate (px)");
+                            ui.add(egui::DragValue::new(&mut m.dilate).range(0..=100));
+                            ui.end_row();
+                            ui.label("Skip faces");
+                            ui.text_edit_singleline(&mut m.skip_faces);
+                            ui.end_row();
+                            ui.label("Batch (faces/GPU)");
+                            ui.add(egui::DragValue::new(&mut m.batch).range(1..=64));
+                            ui.end_row();
+                            ui.label("NMS IoU");
+                            ui.add(
+                                egui::DragValue::new(&mut m.iou)
+                                    .speed(0.01)
+                                    .range(0.0..=1.0)
+                                    .fixed_decimals(2),
+                            );
+                            ui.end_row();
                         });
-                        ui.checkbox(&mut m.empty_if_none, "Write empty (all-keep) mask when no objects detected");
+                    // Optional override for the MIGraphX compiled-model cache dir.
+                    // Leave empty to use the default (~/.cache/pipeline_360/migraphx).
+                    let mut cache_s = m
+                        .ep_cache
+                        .as_ref()
+                        .map(|p| p.display().to_string())
+                        .unwrap_or_default();
+                    ui.horizontal(|ui| {
+                        ui.label("GPU model cache dir:");
+                        let r = ui.text_edit_singleline(&mut cache_s);
+                        if r.changed() {
+                            m.ep_cache = if cache_s.trim().is_empty() {
+                                None
+                            } else {
+                                Some(PathBuf::from(cache_s.trim()))
+                            };
+                        }
+                    });
+                    ui.checkbox(
+                        &mut m.empty_if_none,
+                        "Write empty (all-keep) mask when no objects detected",
+                    );
                 });
 
-                egui::CollapsingHeader::new("Stage 3 — Cubemap (equirect -> 6 faces)")
+                egui::CollapsingHeader::new("Stage 2 — Cubemap (equirect -> 6 faces)").show(
-                    .show(ui, |ui| {
+                    ui,
+                    |ui| {
                         let c = &mut self.cubemap;
-                        egui::Grid::new("cubemap_grid").num_columns(2).spacing([8.0, 4.0]).show(ui, |ui| {
+                        egui::Grid::new("cubemap_grid")
-                            ui.label("Face size");     ui.add(egui::DragValue::new(&mut c.face_size).range(64..=4096)); ui.end_row();
+                            .num_columns(2)
-                            ui.label("Skip faces");    ui.text_edit_singleline(&mut c.skip_faces); ui.end_row();
+                            .spacing([8.0, 4.0])
-                            ui.label("JPEG quality");  ui.add(egui::DragValue::new(&mut c.jpeg_quality).range(1..=100)); ui.end_row();
-                            ui.label("Batch (frames/GPU)"); ui.add(egui::DragValue::new(&mut c.batch).range(1..=32)); ui.end_row();
-                        });
-                    });
-
-                egui::CollapsingHeader::new("Stage 4 — Rig config")
                             .show(ui, |ui| {
+                                ui.label("Face size");
+                                ui.add(egui::DragValue::new(&mut c.face_size).range(64..=4096));
+                                ui.end_row();
+                                ui.label("Skip faces");
+                                ui.text_edit_singleline(&mut c.skip_faces);
+                                ui.end_row();
+                                ui.label("JPEG quality");
+                                ui.add(egui::DragValue::new(&mut c.jpeg_quality).range(1..=100));
+                                ui.end_row();
+                                ui.label("Batch (frames/GPU)");
+                                ui.add(egui::DragValue::new(&mut c.batch).range(1..=32));
+                                ui.end_row();
+                            });
+                    },
+                );
+
+                egui::CollapsingHeader::new("Stage 4 — Rig config").show(ui, |ui| {
                     let r = &mut self.rig;
-                        egui::Grid::new("rig_grid").num_columns(2).spacing([8.0, 4.0]).show(ui, |ui| {
+                    egui::Grid::new("rig_grid")
-                            ui.label("Reference face"); combo(ui, "rig_ref", &["F", "R", "B", "L", "U", "D"], &mut r.ref_face); ui.end_row();
+                        .num_columns(2)
-                            ui.label("Intrinsics");     combo(ui, "rig_int", &["linspace", "half"], &mut r.intrinsics_convention); ui.end_row();
+                        .spacing([8.0, 4.0])
-                            ui.label("Link mode");      combo(ui, "rig_link", &["symlink", "hardlink", "copy"], &mut r.link_mode); ui.end_row();
+                        .show(ui, |ui| {
+                            ui.label("Reference face");
+                            combo(
+                                ui,
+                                "rig_ref",
+                                &["F", "R", "B", "L", "U", "D"],
+                                &mut r.ref_face,
+                            );
+                            ui.end_row();
+                            ui.label("Intrinsics");
+                            combo(
+                                ui,
+                                "rig_int",
+                                &["linspace", "half"],
+                                &mut r.intrinsics_convention,
+                            );
+                            ui.end_row();
+                            ui.label("Link mode");
+                            combo(
+                                ui,
+                                "rig_link",
+                                &["symlink", "hardlink", "copy"],
+                                &mut r.link_mode,
+                            );
+                            ui.end_row();
                         });
                 });
             });

src/stages/extract.rs

@@ -40,7 +40,9 @@ impl Selection {
         match s {
             "chunk" => Ok(Selection::Chunk),
             "spread" => Ok(Selection::Spread),
-            other => Err(anyhow!("unknown --extract-selection `{other}` (chunk|spread)")),
+            other => Err(anyhow!(
+                "unknown --extract-selection `{other}` (chunk|spread)"
+            )),
         }
     }
 }
@@ -62,7 +64,9 @@ impl BadFrameAction {
             "skip" => Ok(BadFrameAction::Skip),
             "keep" => Ok(BadFrameAction::Keep),
             "warn" => Ok(BadFrameAction::Warn),
-            other => Err(anyhow!("unknown --extract-bad-frame-action `{other}` (skip|keep|warn)")),
+            other => Err(anyhow!(
+                "unknown --extract-bad-frame-action `{other}` (skip|keep|warn)"
+            )),
         }
     }
 }
@@ -80,7 +84,9 @@ impl MotionMode {
         match s {
             "off" => Ok(MotionMode::Off),
             "frame_diff" => Ok(MotionMode::FrameDiff),
-            other => Err(anyhow!("unknown --extract-motion-mode `{other}` (off|frame_diff)")),
+            other => Err(anyhow!(
+                "unknown --extract-motion-mode `{other}` (off|frame_diff)"
+            )),
         }
     }
 }
@@ -162,6 +168,16 @@ struct AnalyzeParams {
     pad1: u32,
 }
 
+#[repr(C)]
+#[derive(Clone, Copy)]
+struct ThumbParams {
+    w: u32,
+    h: u32,
+    tw: u32,
+    th: u32,
+    pad0: u32,
+}
+
 /// Owns the wgpu pipeline + a pool of reusable resources for *batched*
 /// per-frame analysis. `batch` frames are uploaded, dispatched in one encoder
 /// and read back with a single `poll(Wait)`, amortising readback latency and
@@ -181,6 +197,14 @@ struct Analyzer<'g> {
     width: u32,
     height: u32,
     batch: usize,
+    /// GPU motion-thumbnail pass (luma `THUMB_W x THUMB_H` per frame).
+    thumb_pipeline: wgpu::ComputePipeline,
+    #[allow(dead_code)]
+    thumb_bgl: wgpu::BindGroupLayout,
+    #[allow(dead_code)]
+    thumb_uniform: wgpu::Buffer,
+    thumb_bufs: Vec<wgpu::Buffer>,
+    thumb_bind_groups: Vec<wgpu::BindGroup>,
 }
 
 fn pod_bytes<T: Copy>(x: &T) -> &[u8] {
@@ -216,98 +240,259 @@ fn reduce_partial(raw: &[u8]) -> (f64, f64, f64) {
 impl<'g> Analyzer<'g> {
     fn new(gpu: &'g GpuContext, width: u32, height: u32, batch: usize) -> Result<Self> {
         let batch = batch.max(1);
-        let bgl = gpu.device.create_bind_group_layout(&wgpu::BindGroupLayoutDescriptor {
+        let bgl = gpu
+            .device
+            .create_bind_group_layout(&wgpu::BindGroupLayoutDescriptor {
                 label: Some("analyze-bgl"),
                 entries: &[
                     wgpu::BindGroupLayoutEntry {
-                    binding: 0, visibility: wgpu::ShaderStages::COMPUTE,
+                        binding: 0,
+                        visibility: wgpu::ShaderStages::COMPUTE,
                         ty: wgpu::BindingType::Buffer {
-                        ty: wgpu::BufferBindingType::Uniform, has_dynamic_offset: false, min_binding_size: None,
+                            ty: wgpu::BufferBindingType::Uniform,
-                    }, count: None,
+                            has_dynamic_offset: false,
+                            min_binding_size: None,
+                        },
+                        count: None,
                     },
                     wgpu::BindGroupLayoutEntry {
-                    binding: 1, visibility: wgpu::ShaderStages::COMPUTE,
+                        binding: 1,
+                        visibility: wgpu::ShaderStages::COMPUTE,
                         ty: wgpu::BindingType::Texture {
                             sample_type: wgpu::TextureSampleType::Float { filterable: false },
-                        view_dimension: wgpu::TextureViewDimension::D2, multisampled: false,
+                            view_dimension: wgpu::TextureViewDimension::D2,
-                    }, count: None,
+                            multisampled: false,
+                        },
+                        count: None,
                     },
                     wgpu::BindGroupLayoutEntry {
-                    binding: 2, visibility: wgpu::ShaderStages::COMPUTE,
+                        binding: 2,
+                        visibility: wgpu::ShaderStages::COMPUTE,
                         ty: wgpu::BindingType::Buffer {
                             ty: wgpu::BufferBindingType::Storage { read_only: false },
-                        has_dynamic_offset: false, min_binding_size: None,
+                            has_dynamic_offset: false,
-                    }, count: None,
+                            min_binding_size: None,
+                        },
+                        count: None,
                     },
                 ],
             });
-        let layout = gpu.device.create_pipeline_layout(&wgpu::PipelineLayoutDescriptor {
+        let layout = gpu
+            .device
+            .create_pipeline_layout(&wgpu::PipelineLayoutDescriptor {
                 label: Some("analyze-layout"),
                 bind_group_layouts: &[&bgl],
                 push_constant_ranges: &[],
             });
-        let pipeline = gpu.compute_pipeline("analyze-pipeline", crate::gpu::shaders::SHARPNESS, &layout);
+        let pipeline =
+            gpu.compute_pipeline("analyze-pipeline", crate::gpu::shaders::SHARPNESS, &layout);
         let n_wg_x = width.div_ceil(16);
         let n_wg_y = height.div_ceil(16);
         let n_wg = (n_wg_x as u64) * (n_wg_y as u64);
         let partial_size = n_wg * 5 * 4;
         let uniform = gpu.create_uniform_buffer(
             "analyze-params",
-            pod_bytes(&AnalyzeParams { width, height, pad0: 0, pad1: 0 }),
+            pod_bytes(&AnalyzeParams {
+                width,
+                height,
+                pad0: 0,
+                pad1: 0,
+            }),
         );
         let mut src_texs = Vec::with_capacity(batch);
         let mut partials = Vec::with_capacity(batch);
         let mut bind_groups = Vec::with_capacity(batch);
         for i in 0..batch {
             let tex = gpu.create_texture_2d(&format!("analyze-src-{i}"), width, height);
-            let partial = gpu.create_storage_buffer(&format!("analyze-partial-{i}"), partial_size, None);
+            let partial =
+                gpu.create_storage_buffer(&format!("analyze-partial-{i}"), partial_size, None);
             let view = tex.create_view(&wgpu::TextureViewDescriptor::default());
             let bg = gpu.device.create_bind_group(&wgpu::BindGroupDescriptor {
                 label: Some(&format!("analyze-bg-{i}")),
                 layout: &bgl,
                 entries: &[
-                    wgpu::BindGroupEntry { binding: 0, resource: uniform.as_entire_binding() },
+                    wgpu::BindGroupEntry {
-                    wgpu::BindGroupEntry { binding: 1, resource: wgpu::BindingResource::TextureView(&view) },
+                        binding: 0,
-                    wgpu::BindGroupEntry { binding: 2, resource: partial.as_entire_binding() },
+                        resource: uniform.as_entire_binding(),
+                    },
+                    wgpu::BindGroupEntry {
+                        binding: 1,
+                        resource: wgpu::BindingResource::TextureView(&view),
+                    },
+                    wgpu::BindGroupEntry {
+                        binding: 2,
+                        resource: partial.as_entire_binding(),
+                    },
                 ],
             });
             src_texs.push(tex);
             partials.push(partial);
             bind_groups.push(bg);
         }
-        Ok(Analyzer { gpu, pipeline, bgl, uniform, src_texs, partials, bind_groups, n_wg_x, n_wg_y, width, height, batch })
+        // Motion-thumbnail pass: one thread per thumbnail pixel writes its luma
+        // into a per-frame storage buffer (motion/parallax proxy on the GPU).
+        let thumb_bgl = gpu
+            .device
+            .create_bind_group_layout(&wgpu::BindGroupLayoutDescriptor {
+                label: Some("thumb-bgl"),
+                entries: &[
+                    wgpu::BindGroupLayoutEntry {
+                        binding: 0,
+                        visibility: wgpu::ShaderStages::COMPUTE,
+                        ty: wgpu::BindingType::Buffer {
+                            ty: wgpu::BufferBindingType::Uniform,
+                            has_dynamic_offset: false,
+                            min_binding_size: None,
+                        },
+                        count: None,
+                    },
+                    wgpu::BindGroupLayoutEntry {
+                        binding: 1,
+                        visibility: wgpu::ShaderStages::COMPUTE,
+                        ty: wgpu::BindingType::Texture {
+                            sample_type: wgpu::TextureSampleType::Float { filterable: false },
+                            view_dimension: wgpu::TextureViewDimension::D2,
+                            multisampled: false,
+                        },
+                        count: None,
+                    },
+                    wgpu::BindGroupLayoutEntry {
+                        binding: 2,
+                        visibility: wgpu::ShaderStages::COMPUTE,
+                        ty: wgpu::BindingType::Buffer {
+                            ty: wgpu::BufferBindingType::Storage { read_only: false },
+                            has_dynamic_offset: false,
+                            min_binding_size: None,
+                        },
+                        count: None,
+                    },
+                ],
+            });
+        let thumb_layout = gpu
+            .device
+            .create_pipeline_layout(&wgpu::PipelineLayoutDescriptor {
+                label: Some("thumb-layout"),
+                bind_group_layouts: &[&thumb_bgl],
+                push_constant_ranges: &[],
+            });
+        let thumb_pipeline = gpu.compute_pipeline(
+            "thumb-pipeline",
+            crate::gpu::shaders::THUMBNAIL,
+            &thumb_layout,
+        );
+        let thumb_uniform = gpu.create_uniform_buffer(
+            "thumb-params",
+            pod_bytes(&ThumbParams {
+                w: width,
+                h: height,
+                tw: THUMB_W,
+                th: THUMB_H,
+                pad0: 0,
+            }),
+        );
+        let thumb_size = (THUMB_W * THUMB_H * 4) as u64;
+        let mut thumb_bufs = Vec::with_capacity(batch);
+        let mut thumb_bind_groups = Vec::with_capacity(batch);
+        for i in 0..batch {
+            let tb = gpu.create_storage_buffer(&format!("thumb-{i}"), thumb_size, None);
+            let view = src_texs[i].create_view(&wgpu::TextureViewDescriptor::default());
+            let bg = gpu.device.create_bind_group(&wgpu::BindGroupDescriptor {
+                label: Some(&format!("thumb-bg-{i}")),
+                layout: &thumb_bgl,
+                entries: &[
+                    wgpu::BindGroupEntry {
+                        binding: 0,
+                        resource: thumb_uniform.as_entire_binding(),
+                    },
+                    wgpu::BindGroupEntry {
+                        binding: 1,
+                        resource: wgpu::BindingResource::TextureView(&view),
+                    },
+                    wgpu::BindGroupEntry {
+                        binding: 2,
+                        resource: tb.as_entire_binding(),
+                    },
+                ],
+            });
+            thumb_bufs.push(tb);
+            thumb_bind_groups.push(bg);
+        }
+        Ok(Analyzer {
+            gpu,
+            pipeline,
+            bgl,
+            uniform,
+            src_texs,
+            partials,
+            bind_groups,
+            n_wg_x,
+            n_wg_y,
+            width,
+            height,
+            batch,
+            thumb_pipeline,
+            thumb_bgl,
+            thumb_uniform,
+            thumb_bufs,
+            thumb_bind_groups,
+        })
     }
 
     /// Upload + dispatch a batch of frames (len <= `batch`) in one encoder.
+    /// Runs both the sharpness pass and the motion-thumbnail pass per frame.
     fn submit_batch(&self, frames: &[&[u8]]) -> Result<()> {
         let n = frames.len();
         debug_assert!(n <= self.batch);
         // Upload all frames first (separate queue writes), then encode dispatches.
         for (i, rgba) in frames.iter().enumerate() {
-            self.gpu.upload_rgba(&self.src_texs[i], self.width, self.height, rgba);
+            self.gpu
+                .upload_rgba(&self.src_texs[i], self.width, self.height, rgba);
         }
-        let mut encoder = self.gpu.device.create_command_encoder(&wgpu::CommandEncoderDescriptor { label: None });
+        let mut encoder = self
+            .gpu
+            .device
+            .create_command_encoder(&wgpu::CommandEncoderDescriptor { label: None });
         {
             let mut pass = encoder.begin_compute_pass(&wgpu::ComputePassDescriptor {
-                label: Some("analyze-pass"), timestamp_writes: None,
+                label: Some("analyze-pass"),
+                timestamp_writes: None,
             });
             pass.set_pipeline(&self.pipeline);
             for i in 0..n {
                 pass.set_bind_group(0, &self.bind_groups[i], &[]);
                 pass.dispatch_workgroups(self.n_wg_x, self.n_wg_y, 1);
             }
+            // Motion-thumbnail pass (read-only src, write luma thumbnail).
+            pass.set_pipeline(&self.thumb_pipeline);
+            let thumb_wgs = (THUMB_W * THUMB_H).div_ceil(256);
+            for i in 0..n {
+                pass.set_bind_group(0, &self.thumb_bind_groups[i], &[]);
+                pass.dispatch_workgroups(thumb_wgs, 1, 1);
+            }
         }
         self.gpu.queue.submit(Some(encoder.finish()));
         Ok(())
     }
 
-    /// Read back a batch of `n` partial buffers with one poll and reduce.
+    /// Read back a batch of `n` partial buffers + thumbnails with one poll.
-    fn collect_batch(&self, n: usize) -> Result<Vec<(f64, f64, f64)>> {
+    /// Returns `(sharpness/exposure/contrast, thumbnails)` per frame.
-        let size = (self.n_wg_x as u64) * (self.n_wg_y as u64) * 5 * 4;
+    fn collect_batch(&self, n: usize) -> Result<(Vec<(f64, f64, f64)>, Vec<Vec<u8>>)> {
-        let srcs: Vec<&wgpu::Buffer> = self.partials[..n].iter().collect();
+        let psize = (self.n_wg_x as u64) * (self.n_wg_y as u64) * 5 * 4;
-        let sizes = vec![size; n];
+        let mut srcs: Vec<&wgpu::Buffer> = self.partials[..n].iter().collect();
+        let mut sizes: Vec<u64> = vec![psize; n];
+        let tsize = (THUMB_W * THUMB_H * 4) as u64;
+        srcs.extend(self.thumb_bufs[..n].iter());
+        sizes.extend(vec![tsize; n]);
         let raws = self.gpu.readback_many(&srcs, &sizes)?;
-        Ok(raws.iter().map(|r| reduce_partial(r)).collect())
+        let mut metrics = Vec::with_capacity(n);
+        let mut thumbs = Vec::with_capacity(n);
+        for r in &raws[..n] {
+            metrics.push(reduce_partial(r));
+        }
+        for r in &raws[n..] {
+            thumbs.push(r.clone());
+        }
+        Ok((metrics, thumbs))
     }
 }
 
@@ -318,24 +503,6 @@ impl<'g> Analyzer<'g> {
 const THUMB_W: u32 = 64;
 const THUMB_H: u32 = 32;
 
-/// Build a tiny grayscale thumbnail (THUMB_W x THUMB_H) from RGBA.
-fn thumbnail(rgba: &[u8], w: u32, h: u32) -> Vec<u8> {
-    let mut out = vec![0u8; (THUMB_W * THUMB_H) as usize];
-    for ty in 0..THUMB_H {
-        for tx in 0..THUMB_W {
-            // Nearest-sample into the source frame.
-            let sx = (u64::from(tx) * u64::from(w) / u64::from(THUMB_W)) as usize;
-            let sy = (u64::from(ty) * u64::from(h) / u64::from(THUMB_H)) as usize;
-            let i = (sy * w as usize + sx) * 4;
-            let r = rgba[i] as f32;
-            let g = rgba[i + 1] as f32;
-            let b = rgba[i + 2] as f32;
-            out[ty as usize * THUMB_W as usize + tx as usize] = (0.299 * r + 0.587 * g + 0.114 * b) as u8;
-        }
-    }
-    out
-}
-
 /// Mean absolute luminance difference between two thumbnails, in 0..255.
 fn frame_motion(a: &[u8], b: &[u8]) -> f64 {
     if a.len() != b.len() {
@@ -377,12 +544,30 @@ fn read_metadata(path: &Path) -> Result<Vec<FrameMetrics>> {
         }
         let mut it = line.split(',');
         let frame = it.next().and_then(|s| s.trim().parse::<u64>().ok());
-        let sharp = it.next().and_then(|s| s.trim().parse::<f64>().ok()).unwrap_or(0.0);
+        let sharp = it
-        let exposure = it.next().and_then(|s| s.trim().parse::<f64>().ok()).unwrap_or(0.0);
+            .next()
-        let contrast = it.next().and_then(|s| s.trim().parse::<f64>().ok()).unwrap_or(0.0);
+            .and_then(|s| s.trim().parse::<f64>().ok())
-        let motion = it.next().and_then(|s| s.trim().parse::<f64>().ok()).unwrap_or(0.0);
+            .unwrap_or(0.0);
+        let exposure = it
+            .next()
+            .and_then(|s| s.trim().parse::<f64>().ok())
+            .unwrap_or(0.0);
+        let contrast = it
+            .next()
+            .and_then(|s| s.trim().parse::<f64>().ok())
+            .unwrap_or(0.0);
+        let motion = it
+            .next()
+            .and_then(|s| s.trim().parse::<f64>().ok())
+            .unwrap_or(0.0);
         if let Some(frame) = frame {
-            out.push(FrameMetrics { frame, sharpness: sharp, exposure, contrast, motion });
+            out.push(FrameMetrics {
+                frame,
+                sharpness: sharp,
+                exposure,
+                contrast,
+                motion,
+            });
         }
     }
     Ok(out)
@@ -431,7 +616,8 @@ fn select_frames(cfg: &ExtractConfig, metrics: &[FrameMetrics]) -> Vec<u64> {
                 let end = (i + chunk).min(metrics.len());
                 let window = &metrics[i..end];
                 // Prefer the sharpest surviving frame; fall back per bad-frame-action.
-                let survivors: Vec<&FrameMetrics> = window.iter().filter(|m| passes(cfg, m)).collect();
+                let survivors: Vec<&FrameMetrics> =
+                    window.iter().filter(|m| passes(cfg, m)).collect();
                 let pick = survivors
                     .iter()
                     .max_by(|a, b| a.sharpness.partial_cmp(&b.sharpness).unwrap())
@@ -440,12 +626,10 @@ fn select_frames(cfg: &ExtractConfig, metrics: &[FrameMetrics]) -> Vec<u64> {
                     Some(m) => Some(m.frame),
                     None => match cfg.bad_frame_action {
                         BadFrameAction::Skip => None,
-                        BadFrameAction::Warn | BadFrameAction::Keep => {
+                        BadFrameAction::Warn | BadFrameAction::Keep => window
-                            window
                             .iter()
                             .max_by(|a, b| a.sharpness.partial_cmp(&b.sharpness).unwrap())
-                                .map(|m| m.frame)
+                            .map(|m| m.frame),
-                        }
                     },
                 };
                 if let Some(f) = chosen {
@@ -465,7 +649,11 @@ fn select_frames(cfg: &ExtractConfig, metrics: &[FrameMetrics]) -> Vec<u64> {
             let mut survivors: Vec<&FrameMetrics> =
                 metrics.iter().filter(|m| passes(cfg, m)).collect();
             survivors.sort_by(|a, b| b.sharpness.partial_cmp(&a.sharpness).unwrap());
-            let target = if cfg.target_count == 0 { survivors.len() as u32 } else { cfg.target_count };
+            let target = if cfg.target_count == 0 {
+                survivors.len() as u32
+            } else {
+                cfg.target_count
+            };
             let mut accepted: Vec<u64> = Vec::new();
             for m in survivors {
                 if accepted.len() as u32 >= target {
@@ -490,7 +678,12 @@ fn select_frames(cfg: &ExtractConfig, metrics: &[FrameMetrics]) -> Vec<u64> {
 // ===========================================================================
 
 /// Format a printf-style pattern with one integer (supports `%d`, `%05d`, …).
-pub fn format_output_filename(pattern: &str, index: u32, output_format: &str, prefix: &str) -> Result<String> {
+pub fn format_output_filename(
+    pattern: &str,
+    index: u32,
+    output_format: &str,
+    prefix: &str,
+) -> Result<String> {
     // Find the single `%[flags][width]d` token and substitute.
     let bytes = pattern.as_bytes();
     let mut out = String::new();
@@ -521,9 +714,21 @@ pub fn format_output_filename(pattern: &str, index: u32, output_format: &str, pr
     let composed = format!("{prefix}{out}");
     let path = Path::new(&composed);
     let target_suffix = format!(".{output_format}");
-    let final_name = if path.extension().map(|e| e.to_string_lossy().to_lowercase()).as_deref() == Some("jpg")
+    let final_name = if path
-        || path.extension().map(|e| e.to_string_lossy().to_lowercase()).as_deref() == Some("jpeg")
+        .extension()
-        || path.extension().map(|e| e.to_string_lossy().to_lowercase()).as_deref() == Some("png")
+        .map(|e| e.to_string_lossy().to_lowercase())
+        .as_deref()
+        == Some("jpg")
+        || path
+            .extension()
+            .map(|e| e.to_string_lossy().to_lowercase())
+            .as_deref()
+            == Some("jpeg")
+        || path
+            .extension()
+            .map(|e| e.to_string_lossy().to_lowercase())
+            .as_deref()
+            == Some("png")
     {
         path.with_extension(target_suffix.trim_start_matches('.'))
             .to_string_lossy()
@@ -540,7 +745,14 @@ pub fn format_output_filename(pattern: &str, index: u32, output_format: &str, pr
 // Frame writing
 // ===========================================================================
 
-fn save_frame(rgba: &[u8], w: u32, h: u32, path: &Path, jpeg_quality: u32, output_format: &str) -> Result<()> {
+fn save_frame(
+    rgba: &[u8],
+    w: u32,
+    h: u32,
+    path: &Path,
+    jpeg_quality: u32,
+    output_format: &str,
+) -> Result<()> {
     if let Some(parent) = path.parent() {
         std::fs::create_dir_all(parent)?;
     }
@@ -552,8 +764,10 @@ fn save_frame(rgba: &[u8], w: u32, h: u32, path: &Path, jpeg_quality: u32, outpu
     };
     if fmt == image::ImageFormat::Jpeg {
         let rgb = image::DynamicImage::ImageRgba8(img).to_rgb8();
-        let mut out = std::fs::File::create(path).with_context(|| format!("cannot create {}", path.display()))?;
+        let mut out = std::fs::File::create(path)
-        let mut enc = image::codecs::jpeg::JpegEncoder::new_with_quality(&mut out, jpeg_quality as u8);
+            .with_context(|| format!("cannot create {}", path.display()))?;
+        let mut enc =
+            image::codecs::jpeg::JpegEncoder::new_with_quality(&mut out, jpeg_quality as u8);
         enc.encode_image(&image::DynamicImage::ImageRgb8(rgb))
             .with_context(|| format!("cannot encode jpeg {}", path.display()))?;
     } else {
@@ -614,18 +828,32 @@ fn analyze_video(
         }
         let refs: Vec<&[u8]> = buf.iter().map(|v| v.as_slice()).collect();
         analyzer.submit_batch(&refs)?;
-        let results = analyzer.collect_batch(refs.len())?;
+        let (metrics_b, thumbs_b) = analyzer.collect_batch(refs.len())?;
-        for (i, (sharp, exp, contrast)) in results.into_iter().enumerate() {
+        for (i, (sharp, exp, contrast)) in metrics_b.into_iter().enumerate() {
-            let rgba = &buf[i];
             let motion = if want_motion {
-                let thumb = thumbnail(rgba, w, h);
+                // Thumbnails come back from the GPU as an `array<f32>` of luma
-                let m = prev_thumb.as_ref().map(|p| frame_motion(&thumb, p)).unwrap_or(0.0);
+                // (0..255). Decode each 4-byte element to an f32, then round to
-                prev_thumb = Some(thumb);
+                // u8 for the cheap CPU motion diff.
+                let thumb_u8: Vec<u8> = thumbs_b[i]
+                    .chunks_exact(4)
+                    .map(|px| f32::from_le_bytes([px[0], px[1], px[2], px[3]]).round() as u8)
+                    .collect();
+                let m = prev_thumb
+                    .as_ref()
+                    .map(|p| frame_motion(&thumb_u8, p))
+                    .unwrap_or(0.0);
+                prev_thumb = Some(thumb_u8);
                 m
             } else {
                 0.0
             };
-            metrics.push(FrameMetrics { frame: frame_no, sharpness: sharp, exposure: exp, contrast, motion });
+            metrics.push(FrameMetrics {
+                frame: frame_no,
+                sharpness: sharp,
+                exposure: exp,
+                contrast,
+                motion,
+            });
             frame_no += 1;
         }
         if frame_no.is_multiple_of(50) || buf.len() < batch {
@@ -660,7 +888,12 @@ fn extract_frames(
     std::fs::create_dir_all(output_dir)?;
     let targets: std::collections::BTreeSet<u64> = selected.iter().copied().collect();
     logging::emit(
-        &format!("Extracting {} frames at {}x{}…", targets.len(), probe.width, probe.height),
+        &format!(
+            "Extracting {} frames at {}x{}…",
+            targets.len(),
+            probe.width,
+            probe.height
+        ),
         logger,
     );
     let mut pipe = FramePipe::open(path, 0, probe)?;
@@ -670,8 +903,20 @@ fn extract_frames(
     while let Some(rgba) = pipe.next_frame()? {
         should_cancel.check().map_err(|_| anyhow!("Cancelled."))?;
         if targets.contains(&frame_no) {
-            let name = format_output_filename(&cfg.output_pattern, output_index, &cfg.output_format, prefix)?;
+            let name = format_output_filename(
-            save_frame(&rgba, pipe.width, pipe.height, &output_dir.join(name), cfg.jpeg_quality, &cfg.output_format)?;
+                &cfg.output_pattern,
+                output_index,
+                &cfg.output_format,
+                prefix,
+            )?;
+            save_frame(
+                &rgba,
+                pipe.width,
+                pipe.height,
+                &output_dir.join(name),
+                cfg.jpeg_quality,
+                &cfg.output_format,
+            )?;
             output_index += 1;
             saved += 1;
             logging::emit_progress(&format!("extracted {saved}/{}", targets.len()), logger);
@@ -683,7 +928,11 @@ fn extract_frames(
     }
     pipe.close();
     if saved != targets.len() {
-        bail!("Some selected frames could not be extracted. Expected {}, saved {}.", targets.len(), saved);
+        bail!(
+            "Some selected frames could not be extracted. Expected {}, saved {}.",
+            targets.len(),
+            saved
+        );
     }
     Ok(saved)
 }
@@ -693,10 +942,17 @@ fn per_video_prefixes(videos: &[PathBuf]) -> Vec<String> {
     let mut used: std::collections::HashMap<String, u32> = std::collections::HashMap::new();
     let mut out = Vec::with_capacity(videos.len());
     for v in videos {
-        let base = v.file_stem().map(|s| s.to_string_lossy().to_string()).unwrap_or_default();
+        let base = v
+            .file_stem()
+            .map(|s| s.to_string_lossy().to_string())
+            .unwrap_or_default();
         let n = used.entry(base.clone()).or_insert(0);
         *n += 1;
-        out.push(if *n == 1 { base } else { format!("{base}_{}", *n) });
+        out.push(if *n == 1 {
+            base
+        } else {
+            format!("{base}_{}", *n)
+        });
     }
     out
 }
@@ -733,7 +989,15 @@ pub fn run_extract_stage(
     for (idx, (video, prefix)) in videos.iter().zip(prefixes.iter()).enumerate() {
         should_cancel.check().map_err(|_| anyhow!("Cancelled."))?;
         if multi {
-            logging::emit(&format!("--- Source {}/{}: {} ---", idx + 1, videos.len(), video.display()), logger);
+            logging::emit(
+                &format!(
+                    "--- Source {}/{}: {} ---",
+                    idx + 1,
+                    videos.len(),
+                    video.display()
+                ),
+                logger,
+            );
         }
         let tag = if multi { prefix.as_str() } else { "" };
         let metadata_path = output_dir.join(if multi {
@@ -744,18 +1008,36 @@ pub fn run_extract_stage(
 
         let probe = video::probe(video)?;
         logging::emit(
-            &format!("Video: {}x{} {} fps, {} frames declared",
+            &format!(
-                probe.width, probe.height,
+                "Video: {}x{} {} fps, {} frames declared",
-                probe.fps_f64().map(|f| format!("{f:.3}")).unwrap_or_else(|| "?".into()),
+                probe.width,
-                probe.nb_frames.map(|n| n.to_string()).unwrap_or_else(|| "?".into())),
+                probe.height,
+                probe
+                    .fps_f64()
+                    .map(|f| format!("{f:.3}"))
+                    .unwrap_or_else(|| "?".into()),
+                probe
+                    .nb_frames
+                    .map(|n| n.to_string())
+                    .unwrap_or_else(|| "?".into())
+            ),
             logger,
         );
 
         let metrics = if metadata_path.exists() && cfg.reuse_metadata {
-            logging::emit(&format!("Using existing sharpness metadata: {}", metadata_path.display()), logger);
+            logging::emit(
+                &format!(
+                    "Using existing sharpness metadata: {}",
+                    metadata_path.display()
+                ),
+                logger,
+            );
             read_metadata(&metadata_path)?
         } else {
-            logging::emit(&format!("Generating sharpness metadata: {}", metadata_path.display()), logger);
+            logging::emit(
+                &format!("Generating sharpness metadata: {}", metadata_path.display()),
+                logger,
+            );
             let m = analyze_video(gpu, video, &probe, cfg, should_cancel, logger)?;
             write_metadata(&metadata_path, &m)?;
             m
@@ -766,21 +1048,46 @@ pub fn run_extract_stage(
         let n_rejected = metrics.len() - n_survivors;
         if n_rejected > 0 {
             logging::emit(
-                &format!("Quality filter: {n_rejected}/{} frames rejected (thresholds).", metrics.len()),
+                &format!(
+                    "Quality filter: {n_rejected}/{} frames rejected (thresholds).",
+                    metrics.len()
+                ),
                 logger,
             );
         }
         logging::emit(
-            &format!("Selected {}/{} frames (mode={:?}, chunk={}, gap={}).",
+            &format!(
-                selected.len(), metrics.len(), cfg.selection, cfg.chunk_size, cfg.min_gap),
+                "Selected {}/{} frames (mode={:?}, chunk={}, gap={}).",
+                selected.len(),
+                metrics.len(),
+                cfg.selection,
+                cfg.chunk_size,
+                cfg.min_gap
+            ),
             logger,
         );
 
-        let saved = extract_frames(video, &probe, &selected, output_dir, cfg, tag, should_cancel, logger)?;
+        let saved = extract_frames(
-        outcomes.push(ExtractOutcome { video: video.to_path_buf(), prefix: prefix.clone(), frames_written: saved });
+            video,
+            &probe,
+            &selected,
+            output_dir,
+            cfg,
+            tag,
+            should_cancel,
+            logger,
+        )?;
+        outcomes.push(ExtractOutcome {
+            video: video.to_path_buf(),
+            prefix: prefix.clone(),
+            frames_written: saved,
+        });
     }
 
     logging::emit("Done: sharp frames extracted.", logger);
-    logging::emit(&format!("Output directory: {}", output_dir.display()), logger);
+    logging::emit(
+        &format!("Output directory: {}", output_dir.display()),
+        logger,
+    );
     Ok(outcomes)
 }