Fuse semantic segmentation mask into the trimap

Wire BiRefNet into the pipeline (lazy-loaded) and build the trimap from the
semantic subject mask refined by the green key, used when segmentation is
enabled. generate_trimap (chroma-only) stays as the no-segmentation fallback.

Authority split: the mask decides subject topology (keeps green-tinted hair as
foreground, drops see-through holes), the bright-green key sharpens the screen
boundary, ViTMatte refines a small protective band. Background follows the mask
directly so interior holes survive; the band is small so it does not swallow
finger gaps.

End-to-end on the samples: green hair preserved, finger-gap green 99%
transparent (BiRefNet marks it background; was 100% foreground before), leg
edges smooth -- topology/colour/edge problems local cues could not solve, with
no hard alpha surgery.

- SegmentationSettings wired into PipelineSettings/config; --device propagates.
- TrimapSettings: seg_core_threshold, seg_loose_threshold.
- New debug output seg_mask.png.

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

configs/default.yaml

@@ -4,11 +4,19 @@ model:
   matting_method: vitmatte
   fallback_to_chroma_alpha: false
 
+segmentation:
+  enabled: true
+  model_name: ZhengPeng7/BiRefNet
+  device: cuda
+  input_size: 1024
+
 trimap:
   sure_bg_threshold: 0.92
   sure_fg_threshold: 0.12
   unknown_radius_ratio: 0.012
   fg_safe_radius_ratio: 0.006
+  seg_core_threshold: 0.60
+  seg_loose_threshold: 0.15
 
 alpha_post:
   chroma_suppress: true