nv12: convert with the source colorspace matrix (not hardcoded BT.709)

The NV12→RGB pass hardcoded BT.709, so SD (BT.601) clips had slightly wrong hues.
Read each frame's AVColorSpace in the importer and derive the Y'CbCr→R'G'B'
matrix (BT.709/601/240M/2020; Unspecified guessed by height like swscale/players),
carry the four coefficients on GpuVideoFrame, and apply them in the shader.

- core: GpuVideoFrame.coeffs + ycbcr_coeffs(kr, kb) helper.
- hw_video.rs: map AVColorSpace → (kr, kb) → coeffs.
- nv12_blit{.rs,.wgsl}: uniform grows to 80 bytes (adds a coeffs vec4); the matrix
  multiply uses params.coeffs instead of literals.

BT.2020's transfer is still approximated as sRGB. The DRM-modifier-without-SAMPLED case stays a graceful software fallback.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

lightningbeam-ui/lightningbeam-core/src/video.rs

@@ -715,6 +715,22 @@ pub struct GpuVideoFrame {
     /// Source YUV range: true = full/PC (0–255), false = limited/TV (16–235). Drives the NV12→RGB
     /// offset/scale in the compositor.
     pub full_range: bool,
+    /// Y'CbCr→R'G'B' matrix coefficients derived from the frame's colorspace (BT.709/601/2020),
+    /// so SD (BT.601) and HD/UHD clips each convert correctly: `[Cr→R, Cb→G, Cr→G, Cb→B]`.
+    ///   R = Y + c[0]·Cr,  G = Y + c[1]·Cb + c[2]·Cr,  B = Y + c[3]·Cb
+    pub coeffs: [f32; 4],
+}
+
+/// Y'CbCr→R'G'B' matrix coefficients (`[Cr→R, Cb→G, Cr→G, Cb→B]`) from the luma weights `kr`/`kb`
+/// (`kg = 1−kr−kb`). BT.709 → `[1.5748, −0.1873, −0.4681, 1.8556]`.
+pub fn ycbcr_coeffs(kr: f32, kb: f32) -> [f32; 4] {
+    let kg = 1.0 - kr - kb;
+    [
+        2.0 * (1.0 - kr),
+        -2.0 * kb * (1.0 - kb) / kg,
+        -2.0 * kr * (1.0 - kr) / kg,
+        2.0 * (1.0 - kb),
+    ]
 }
 
 /// Imports a decoded VAAPI surface (a `*mut AVFrame`, passed as an opaque pointer so core needn't

lightningbeam-ui/lightningbeam-editor/src/hw_video.rs

@@ -6,7 +6,9 @@
 
 use ffmpeg_next::ffi as ff;
 use gpu_video_encoder::dmabuf::{self, Nv12DmaBuf};
-use lightningbeam_core::video::{GpuVideoFrame, HwDeviceHandle, HwVideoImporter, VideoManager};
+use lightningbeam_core::video::{
+    ycbcr_coeffs, GpuVideoFrame, HwDeviceHandle, HwVideoImporter, VideoManager,
+};
 use std::sync::{Arc, Mutex};
 
 /// Imports decoded VAAPI surfaces onto the shared wgpu device. Holds clones of the shared
@@ -52,6 +54,29 @@ impl HwVideoImporter for SharedHwImporter {
         };
         let full_range = (*frame).color_range == ff::AVColorRange::AVCOL_RANGE_JPEG;
 
+        // Luma weights (kr, kb) from the frame's matrix coefficients, so SD (BT.601) and HD/UHD
+        // (BT.709) clips each convert with the right matrix. Unspecified → guess by height, as
+        // players/swscale do. SMPTE240M and BT.2020 are handled too (the latter's transfer is still
+        // approximated as sRGB — fine for SDR; true HDR is out of scope).
+        let (kr, kb) = match (*frame).colorspace {
+            ff::AVColorSpace::AVCOL_SPC_BT709 => (0.2126, 0.0722),
+            ff::AVColorSpace::AVCOL_SPC_BT470BG | ff::AVColorSpace::AVCOL_SPC_SMPTE170M => {
+                (0.299, 0.114)
+            }
+            ff::AVColorSpace::AVCOL_SPC_SMPTE240M => (0.212, 0.087),
+            ff::AVColorSpace::AVCOL_SPC_BT2020_NCL | ff::AVColorSpace::AVCOL_SPC_BT2020_CL => {
+                (0.2627, 0.0593)
+            }
+            _ => {
+                if height <= 576 {
+                    (0.299, 0.114) // SD → BT.601
+                } else {
+                    (0.2126, 0.0722) // HD/UHD → BT.709
+                }
+            }
+        };
+        let coeffs = ycbcr_coeffs(kr, kb);
+
         let imported = dmabuf::import_raw(&self.device, &self.adapter, &buf);
         ff::av_frame_free(&mut (drm_f as *mut _)); // the fd was dup'd into Vulkan
         let (y, uv) = imported.ok()?.into_planes();
@@ -61,6 +86,7 @@ impl HwVideoImporter for SharedHwImporter {
             width,
             height,
             full_range,
+            coeffs,
         })
     }
 }

lightningbeam-ui/lightningbeam-editor/src/nv12_blit.rs

@@ -5,12 +5,13 @@
 
 use crate::gpu_brush::BlitTransform;
 
-/// Uniform: the `viewport_uv → frame_uv` affine (same packing as [`BlitTransform`]) plus the
-/// full-range flag. 64 bytes (48 for the matrix + a u32 + 12 padding).
+/// Uniform: the `viewport_uv → frame_uv` affine (same packing as [`BlitTransform`]), the Y'CbCr→RGB
+/// matrix coefficients, and the full-range flag. 80 bytes (48 matrix + 16 coeffs + u32 + 12 pad).
 #[repr(C)]
 #[derive(Clone, Copy, bytemuck::Pod, bytemuck::Zeroable)]
 struct Nv12Params {
     transform: BlitTransform,
+    coeffs: [f32; 4],
     full_range: u32,
     _pad: [u32; 3],
 }
@@ -127,9 +128,11 @@ impl Nv12BlitPipeline {
         target_view: &wgpu::TextureView,
         transform: &BlitTransform,
         full_range: bool,
+        coeffs: [f32; 4],
     ) {
         let params = Nv12Params {
             transform: *transform,
+            coeffs,
             full_range: full_range as u32,
             _pad: [0; 3],
         };

lightningbeam-ui/lightningbeam-editor/src/panes/shaders/nv12_blit.wgsl

@@ -14,8 +14,10 @@ struct Nv12Params {
     col0: vec4<f32>,
     col1: vec4<f32>,
     col2: vec4<f32>,
-    // .x = full_range flag; .yzw padding. A vec4 keeps the struct 64 bytes (matching the Rust
-    // `u32 + [u32; 3]`); a bare u32 + vec3 would round up to 80 and mismatch the bound buffer.
+    // Y'CbCr→R'G'B' matrix from the source colorspace: [Cr→R, Cb→G, Cr→G, Cb→B].
+    coeffs: vec4<f32>,
+    // .x = full_range flag; .yzw padding. A vec4 keeps each block 16-aligned and the struct size
+    // matching the Rust `[f32;4] + u32 + [u32;3]` (80 bytes).
     flags: vec4<u32>,
 }
 
@@ -73,10 +75,10 @@ fn fs_main(in: VertexOutput) -> @location(0) vec4<f32> {
         Cr = (cbcr.g * 255.0 - 128.0) / 224.0;
     }
 
-    // BT.709 Y'CbCr → gamma-encoded R'G'B'.
-    let r = Y + 1.5748 * Cr;
-    let g = Y - 0.1873 * Cb - 0.4681 * Cr;
-    let b = Y + 1.8556 * Cb;
+    // Y'CbCr → gamma-encoded R'G'B' using the source colorspace's matrix.
+    let r = Y + params.coeffs.x * Cr;
+    let g = Y + params.coeffs.y * Cb + params.coeffs.z * Cr;
+    let b = Y + params.coeffs.w * Cb;
     let rgb_gamma = clamp(vec3<f32>(r, g, b), vec3<f32>(0.0), vec3<f32>(1.0));
 
     // R'G'B' is gamma-encoded; the HDR target is linear → undo the transfer.

lightningbeam-ui/lightningbeam-editor/src/panes/stage.rs

@@ -1703,7 +1703,7 @@ impl egui_wgpu::CallbackTrait for VelloCallback {
                                     let y_view = gpu.y.create_view(&Default::default());
                                     let uv_view = gpu.uv.create_view(&Default::default());
                                     shared.nv12_blit.blit(
-                                        device, queue, &y_view, &uv_view, hdr_layer_view, &bt, gpu.full_range,
+                                        device, queue, &y_view, &uv_view, hdr_layer_view, &bt, gpu.full_range, gpu.coeffs,
                                     );
                                 } else {
                                     // Reuse the GPU texture for this frame if it's unchanged (a