Add BiRefNet semantic segmentation module

Adds bgfilter/segmentation.py: BiRefNetSegmenter produces a soft subject mask
that defines topology -- it includes colour-contaminated foreground (green-tinted
hair) and excludes see-through holes (finger gaps), the distinction chroma/colour
cues cannot make. Validated on both samples: green hair -> foreground, finger gap
-> background, both correct.

Foundation of the semantic-guided redesign; the mask will drive trimap
construction next, with ViTMatte still refining soft edges.

- SegmentationSettings (ZhengPeng7/BiRefNet, 1024 input, fp32).
- Deps: torchvision, timm, einops, kornia. Weights load from HuggingFace via
  trust_remote_code; behind a firewall set HF_ENDPOINT=https://hf-mirror.com and
  bypass the proxy.

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

bgfilter/settings.py

@@ -78,6 +78,14 @@ class ModelSettings:
     fallback_to_chroma_alpha: bool = False
 
 
+@dataclass(frozen=True)
+class SegmentationSettings:
+    enabled: bool = True
+    model_name: str = "ZhengPeng7/BiRefNet"
+    device: str = "cuda"
+    input_size: int = 1024
+
+
 @dataclass(frozen=True)
 class PipelineSettings:
     chroma: ChromaSettings = ChromaSettings()