lhk229
72655dea91
reuse_as_seg swaps one BiRefNet-family model for another (the validated equivalence); it must not silently override an explicitly chosen anime-seg backend. With --seg-backend anime-seg the segmenter now keeps its own forward and the cross-check veto runs independently on top -- both combinable, no flag juggling. Default birefnet path is untouched (verified byte-identical); anime-seg + cross-check verified to run both models. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
210 lines
7.6 KiB
Python
210 lines
7.6 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
from dataclasses import asdict
|
|
from pathlib import Path
|
|
|
|
import numpy as np
|
|
|
|
from .alpha_post import (
|
|
clean_alpha,
|
|
cross_check_alpha,
|
|
enforce_trimap,
|
|
suppress_alpha_by_chroma,
|
|
)
|
|
from .chroma import (
|
|
bg_hue_projection,
|
|
compute_bg_confidence,
|
|
convert_color_spaces,
|
|
parse_hex_color,
|
|
)
|
|
from .despill import despill
|
|
from .foreground import estimate_foreground_rgb
|
|
from .io import load_rgb, save_gray, save_rgb, save_rgba, write_text
|
|
from .qa import BACKGROUND_COLORS, composite, make_qa_grid, save_previews
|
|
from .settings import PipelineSettings, SegmentationSettings
|
|
from .trimap import (
|
|
fuse_trimap,
|
|
fuse_trimap_directional,
|
|
generate_trimap,
|
|
trimap_to_alpha_seed,
|
|
)
|
|
from .vitmatte_infer import ViTMatteRunner
|
|
|
|
|
|
class MattingPipeline:
|
|
def __init__(self, settings: PipelineSettings):
|
|
self.settings = settings
|
|
self._runner: ViTMatteRunner | None = None
|
|
self._segmenter = None
|
|
self._cross_checker = None
|
|
|
|
def _segment(self, rgb: np.ndarray) -> np.ndarray:
|
|
if self._segmenter is None:
|
|
from .segmentation import make_segmenter
|
|
|
|
self._segmenter = make_segmenter(self.settings.segmentation)
|
|
return self._segmenter.mask(rgb)
|
|
|
|
def _second_opinion(self, rgb: np.ndarray) -> np.ndarray:
|
|
if self._cross_checker is None:
|
|
from .segmentation import BiRefNetSegmenter
|
|
|
|
check = self.settings.cross_check
|
|
self._cross_checker = BiRefNetSegmenter(
|
|
SegmentationSettings(
|
|
model_name=check.model_name,
|
|
device=self.settings.segmentation.device,
|
|
input_size=check.input_size,
|
|
precision=check.precision,
|
|
)
|
|
)
|
|
return self._cross_checker.mask(rgb)
|
|
|
|
def _predict_alpha(self, rgb: np.ndarray, trimap: np.ndarray, bg_confidence: np.ndarray) -> tuple[np.ndarray, str]:
|
|
if self.settings.model.matting_method == "chroma":
|
|
return trimap_to_alpha_seed(trimap, bg_confidence), "chroma"
|
|
if self.settings.model.matting_method != "vitmatte":
|
|
raise RuntimeError(
|
|
f"Unsupported matting method '{self.settings.model.matting_method}'. "
|
|
"Use 'vitmatte' or 'chroma'."
|
|
)
|
|
|
|
try:
|
|
if self._runner is None:
|
|
self._runner = ViTMatteRunner(self.settings.model)
|
|
return self._runner.predict(rgb, trimap), "vitmatte"
|
|
except RuntimeError:
|
|
if not self.settings.model.fallback_to_chroma_alpha:
|
|
raise
|
|
return trimap_to_alpha_seed(trimap, bg_confidence), "chroma_fallback"
|
|
|
|
def run_image(
|
|
self,
|
|
input_path: str | Path,
|
|
output_path: str | Path,
|
|
debug_dir: str | Path | None,
|
|
) -> dict:
|
|
return _run_image(input_path, output_path, debug_dir, self)
|
|
|
|
|
|
def run_image(
|
|
input_path: str | Path,
|
|
output_path: str | Path,
|
|
debug_dir: str | Path | None,
|
|
settings: PipelineSettings,
|
|
) -> dict:
|
|
return MattingPipeline(settings).run_image(input_path, output_path, debug_dir)
|
|
|
|
|
|
def _run_image(
|
|
input_path: str | Path,
|
|
output_path: str | Path,
|
|
debug_dir: str | Path | None,
|
|
pipeline: MattingPipeline,
|
|
) -> dict:
|
|
settings = pipeline.settings
|
|
rgb = load_rgb(input_path)
|
|
screen_color = parse_hex_color(settings.screen_color) if settings.screen_color else None
|
|
bg_confidence, model = compute_bg_confidence(
|
|
rgb, settings=settings.chroma, screen_color=screen_color
|
|
)
|
|
second_alpha = None
|
|
if settings.segmentation.enabled:
|
|
reuse = (
|
|
settings.cross_check.enabled
|
|
and settings.cross_check.reuse_as_seg
|
|
# Reuse swaps one BiRefNet-family model for another (validated
|
|
# equivalent topology). A different backend chosen explicitly
|
|
# (anime-seg) keeps its own forward; cross-check still runs
|
|
# independently on top of it.
|
|
and settings.segmentation.backend == "birefnet"
|
|
)
|
|
if reuse:
|
|
# One HR-matting forward serves both the trimap topology and the
|
|
# cross-check second opinion; the primary seg model is never loaded.
|
|
second_alpha = pipeline._second_opinion(rgb)
|
|
seg_mask = second_alpha
|
|
else:
|
|
seg_mask = pipeline._segment(rgb)
|
|
mode = settings.trimap.mode
|
|
if mode == "seg":
|
|
trimap, trimap_stats = fuse_trimap(seg_mask, bg_confidence, settings.trimap)
|
|
elif mode in ("directional", "directional-hard-bg"):
|
|
lab = convert_color_spaces(rgb)[1]
|
|
trimap, trimap_stats = fuse_trimap_directional(
|
|
seg_mask, bg_confidence, lab, model.lab_center, settings.trimap
|
|
)
|
|
else:
|
|
raise RuntimeError(
|
|
f"Unknown trimap.mode '{mode}'. "
|
|
"Use 'directional', 'seg', or 'directional-hard-bg'."
|
|
)
|
|
else:
|
|
seg_mask = None
|
|
trimap, trimap_stats = generate_trimap(bg_confidence, settings.trimap)
|
|
raw_alpha, alpha_source = pipeline._predict_alpha(rgb, trimap, bg_confidence)
|
|
|
|
alpha = enforce_trimap(raw_alpha, trimap)
|
|
alpha = suppress_alpha_by_chroma(
|
|
alpha, bg_confidence, trimap, settings.alpha_post,
|
|
# The matte-confidence gate only makes sense for a real matting prediction;
|
|
# a chroma-seeded alpha is itself colour evidence, so no gate there.
|
|
raw_alpha=raw_alpha if alpha_source == "vitmatte" else None,
|
|
)
|
|
alpha = clean_alpha(alpha, trimap, settings.alpha_post)
|
|
if settings.cross_check.enabled:
|
|
lab = convert_color_spaces(rgb)[1]
|
|
if second_alpha is None:
|
|
second_alpha = pipeline._second_opinion(rgb)
|
|
alpha = cross_check_alpha(
|
|
alpha,
|
|
second_alpha,
|
|
bg_hue_projection(lab, model.lab_center),
|
|
lab[..., 0],
|
|
trimap,
|
|
settings.cross_check,
|
|
)
|
|
foreground = estimate_foreground_rgb(
|
|
rgb, alpha, bg_confidence, model, settings.foreground
|
|
)
|
|
corrected_rgb, color_mask = despill(
|
|
foreground.rgb, alpha, model, settings.despill
|
|
)
|
|
save_rgba(output_path, corrected_rgb, alpha)
|
|
|
|
result = {
|
|
"input": str(input_path),
|
|
"output": str(output_path),
|
|
"alpha_source": alpha_source,
|
|
"background_model": model.to_dict(),
|
|
"trimap": trimap_stats,
|
|
"settings": asdict(settings),
|
|
}
|
|
|
|
if debug_dir is not None:
|
|
debug = Path(debug_dir)
|
|
debug.mkdir(parents=True, exist_ok=True)
|
|
save_gray(debug / "bg_confidence.png", bg_confidence)
|
|
save_gray(debug / "trimap.png", trimap)
|
|
if seg_mask is not None:
|
|
save_gray(debug / "seg_mask.png", seg_mask)
|
|
if second_alpha is not None:
|
|
save_gray(debug / "cross_check_alpha.png", second_alpha)
|
|
save_gray(debug / "alpha.png", alpha)
|
|
save_rgb(debug / "foreground_rgb.png", corrected_rgb)
|
|
save_gray(debug / "color_mask.png", color_mask)
|
|
save_previews(debug, corrected_rgb, alpha)
|
|
tiles = {
|
|
"input": rgb,
|
|
"bg confidence": np.repeat((bg_confidence[..., None] * 255).astype(np.uint8), 3, axis=2),
|
|
"trimap": np.repeat(trimap[..., None], 3, axis=2),
|
|
"alpha": np.repeat((alpha[..., None] * 255).astype(np.uint8), 3, axis=2),
|
|
}
|
|
for name, color in BACKGROUND_COLORS.items():
|
|
tiles[f"preview {name}"] = composite(corrected_rgb, alpha, color)
|
|
make_qa_grid(debug, tiles)
|
|
write_text(debug / "metadata.json", json.dumps(result, indent=2, ensure_ascii=False))
|
|
|
|
return result
|