BGfilter

Author SHA1 Message Date

Author	SHA1	Message	Date
lhk229	11c591e5b5	Default the HTTP service to cross-check OFF (opt in via BGFILTER_CROSS_CHECK) The cross-model veto adds one extra large-model inference per request (measured ~35 s/image on CPU: 14.4 s -> 49.1 s), which is too slow as a service default. The service now disables it regardless of the config default; BGFILTER_CROSS_CHECK=1 re-enables it (GPU or quality-first deployments). CLI behaviour is unchanged (still on by default). Startup log and /healthz report the effective state. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-04 20:57:39 +08:00
lhk229	578bd1f4d8	Merge master: matte-confidence gate + cross-model hair-gap veto Brings in the two algorithm optimisations from master: - Gate chroma suppression by the matte's own confidence (`639fdf0`) - Add cross-model veto of hair-gap background residue (`adbbb9d`) Server-edition integration on top of the plain merge: - PipelineManager caches the cross-check model (BiRefNet_HR-matting) and injects it into MattingPipeline, so HTTP requests never reload it. - MattingResult carries cross_check_alpha; debug output matches master. - /healthz reports crossCheck; README lists models/BiRefNet_HR-matting in the local-weights bundle. Verified: CLI --no-cross-check baseline and full cross-check run both pass on samples/TestImage3.png; cross_check_alpha.png written to debug. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-07-04 20:37:07 +08:00
lhk229	d24c6ed608	Add FastAPI HTTP service for background removal Wrap the BGfilter matting pipeline in a long-running FastAPI service (POST /remove-background, GET /healthz) exposing only screen_color and seg_model, matching the birefnet-service request contract. - bgfilter/pipeline.py: add in-memory run_rgb entry returning a MattingResult; allow injecting a shared runner/segmenter. CLI file path (run_image) behaviour is unchanged. - bgfilter/service.py: PipelineManager caches one shared ViTMatte runner and per-backend segmenters, so screen_color/seg_model never reload a model. - app.py: thin FastAPI layer -- param validation, image decode/encode, error codes (400/413/500), timing headers, global asyncio lock. - requirements.txt: fastapi, uvicorn[standard], python-multipart. - README + design doc: HTTP service usage and HF-mirror/proxy/Xet download notes. Verified end-to-end (base ViTMatte + BiRefNet + anime-seg): 11/11 acceptance checks pass. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>	2026-07-02 12:08:25 +00:00

11c591e5b5

Default the HTTP service to cross-check OFF (opt in via BGFILTER_CROSS_CHECK)

The cross-model veto adds one extra large-model inference per request
(measured ~35 s/image on CPU: 14.4 s -> 49.1 s), which is too slow as a
service default. The service now disables it regardless of the config
default; BGFILTER_CROSS_CHECK=1 re-enables it (GPU or quality-first
deployments). CLI behaviour is unchanged (still on by default).

Startup log and /healthz report the effective state.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-04 20:57:39 +08:00

lhk229

578bd1f4d8

Merge master: matte-confidence gate + cross-model hair-gap veto

Brings in the two algorithm optimisations from master:
- Gate chroma suppression by the matte's own confidence (639fdf0)
- Add cross-model veto of hair-gap background residue (adbbb9d)

Server-edition integration on top of the plain merge:
- PipelineManager caches the cross-check model (BiRefNet_HR-matting) and
  injects it into MattingPipeline, so HTTP requests never reload it.
- MattingResult carries cross_check_alpha; debug output matches master.
- /healthz reports crossCheck; README lists models/BiRefNet_HR-matting
  in the local-weights bundle.

Verified: CLI --no-cross-check baseline and full cross-check run both
pass on samples/TestImage3.png; cross_check_alpha.png written to debug.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-04 20:37:07 +08:00

lhk229

d24c6ed608

Add FastAPI HTTP service for background removal

Wrap the BGfilter matting pipeline in a long-running FastAPI service
(POST /remove-background, GET /healthz) exposing only screen_color and
seg_model, matching the birefnet-service request contract.

- bgfilter/pipeline.py: add in-memory run_rgb entry returning a
  MattingResult; allow injecting a shared runner/segmenter. CLI file
  path (run_image) behaviour is unchanged.
- bgfilter/service.py: PipelineManager caches one shared ViTMatte runner
  and per-backend segmenters, so screen_color/seg_model never reload a
  model.
- app.py: thin FastAPI layer -- param validation, image decode/encode,
  error codes (400/413/500), timing headers, global asyncio lock.
- requirements.txt: fastapi, uvicorn[standard], python-multipart.
- README + design doc: HTTP service usage and HF-mirror/proxy/Xet
  download notes.

Verified end-to-end (base ViTMatte + BiRefNet + anime-seg): 11/11
acceptance checks pass.

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

2026-07-02 12:08:25 +00:00

3 Commits