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>

This commit is contained in:

孔令弘

2026-06-30 21:07:24 +08:00

parent a9886f1479

commit a6a313d2d0

3 changed files with 85 additions and 0 deletions

requirements.txt

View File

@@ -5,10 +5,14 @@ scipy
 scikit-image
 pymatting
 torch
 torchvision
 transformers
 accelerate
 safetensors
 huggingface_hub
 timm
 einops
 kornia
 tqdm
 typer
 rich