lhk229/BGfilter
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Run the cross-check veto in complex-background mode with a hue-free gate

Browse Source 
The veto's suspect zone was defined by background-hue projection, so
--no-chroma silently skipped it. Without a key colour there is no hue
test to lean on, so in complex mode the gate instead requires the second
opinion itself to be confidently near-empty (second_lo -> second_hi ramp,
default 0.15 -> 0.40): regions the HR-matting model decisively rejects
can be cleared, while thin strands it merely blurs to mid-alpha are
untouched -- protecting exactly the crisp-strand advantage the pipeline
has over a raw BiRefNet mask. Flat mode's gate is unchanged.

Validation (BG_IMAGE01-04, cuda fp32): flat default path bit-identical;
complex-mode veto touches 0.007-0.025% of pixels, visibly clearing
blurred residue near strands and milky specks in hair gaps with no
strand erosion. Costs the HR-matting forward in --no-chroma runs
(0.61 -> 1.6 s/image warm GPU); disable with --no-cross-check.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
孔令弘
2026-07-14 13:09:57 +08:00
parent e61fbe84f0
commit 2b3b62ed3f
5 changed files with 48 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
bgfilter/alpha_post.py
+13 -6
View File
@@ -59,7 +59,7 @@ def suppress_alpha_by_chroma(
def cross_check_alpha(
alpha: np.ndarray,
second_alpha: np.ndarray,
proj: np.ndarray,
proj: np.ndarray | None,
lightness: np.ndarray,
trimap: np.ndarray,
settings: CrossCheckSettings,
@@ -76,6 +76,13 @@ def cross_check_alpha(
- the primary alpha is high (``gate_lo -> gate_hi`` ramp): pixels the
pipeline already renders soft (outer wisps) are exempt by construction.
``proj`` is None in complex-background mode (chroma disabled): no key colour
means no hue-defined suspect zone, so instead the veto requires the second
opinion itself to be confidently near-empty (full strength at/below
``second_lo``, none at/above ``second_hi``). A thin strand the downsampled
second model merely blurs to mid-alpha is left untouched; only regions it
decisively rejects can be cleared.
Inside the zone this deliberately overrides the trimap-FG clamp -- the
residue it exists to clear is mostly trimap-FG. Sure background cannot be
disturbed: min-fusion keeps alpha 0 at 0.
@@ -83,16 +90,16 @@ def cross_check_alpha(
if not settings.enabled:
return alpha
cv2 = require_cv2()
zone = (
(proj >= settings.proj_min)
& (lightness >= settings.l_min)
& (trimap != 0)
)
zone = (lightness >= settings.l_min) & (trimap != 0)
if proj is not None:
zone &= proj >= settings.proj_min
weight = zone.astype(np.float32)
if settings.feather_sigma > 0:
blur = cv2.GaussianBlur(weight, (0, 0), settings.feather_sigma)
weight = np.where(zone, 1.0, np.clip(blur, 0.0, 1.0)).astype(np.float32)
gate = weight * _smoothstep(alpha, settings.gate_lo, settings.gate_hi)
if proj is None:
gate = gate * (1.0 - _smoothstep(second_alpha, settings.second_lo, settings.second_hi))
out = alpha * (1.0 - gate) + np.minimum(alpha, second_alpha) * gate
return np.clip(out, 0.0, 1.0).astype(np.float32)
bgfilter/pipeline.py
+4 -4
View File
@@ -199,16 +199,16 @@ def _process_rgb(rgb: np.ndarray, pipeline: MattingPipeline) -> MattingResult:
raw_alpha=raw_alpha if alpha_source == "vitmatte" else None,
)
alpha = clean_alpha(alpha, trimap, settings.alpha_post)
# The veto's suspect zone is defined by background hue, so it needs the key
# colour; without chroma the second opinion still serves as seg (reuse above).
if settings.cross_check.enabled and settings.chroma.enabled:
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),
# No key colour in complex-background mode: proj=None switches the
# veto to its second-opinion-confidence gate (see cross_check_alpha).
bg_hue_projection(lab, model.lab_center) if model is not None else None,
lab[..., 0],
trimap,
settings.cross_check,
bgfilter/settings.py
+13 -6
View File
@@ -6,12 +6,12 @@ from dataclasses import dataclass
@dataclass(frozen=True)
class ChromaSettings:
# False = non-flat-background mode (--no-chroma): no colour key at all.
# Segmentation alone drives the trimap (mode forced to "seg"), and every
# colour-keyed stage is bypassed: background auto-detect, the directional
# hue split, chroma alpha suppression, despill, the cross-check veto (its
# suspect zone is background-hued by definition; with reuse_as_seg the
# second opinion still serves as the segmenter), and the unmix foreground
# fallback. Requires segmentation.enabled and matting_method 'vitmatte'.
# Segmentation alone drives the trimap (mode forced to "seg"), and the
# colour-keyed stages are bypassed: background auto-detect, the directional
# hue split, chroma alpha suppression, despill, and the unmix foreground
# fallback. The cross-check veto still runs (if enabled) with a hue-free
# gate -- see CrossCheckSettings.second_lo/hi. Requires
# segmentation.enabled and matting_method 'vitmatte'.
enabled: bool = True
border_ratio: float = 0.04
min_samples: int = 2048
@@ -107,6 +107,13 @@ class CrossCheckSettings:
feather_sigma: float = 2.0 # Gaussian feather of the zone boundary, in px
gate_lo: float = 0.70 # primary alpha below this -> fully exempt
gate_hi: float = 0.95 # primary alpha above this -> fully vetoable
# Complex-background mode only (chroma disabled -> no hue-defined suspect
# zone): the veto instead requires the second opinion itself to be
# confidently near-empty -- full strength at/below second_lo, none at/above
# second_hi. Thin structures the downsampled second model merely blurs to
# mid-alpha stay untouched; only decisively-rejected regions can be cleared.
second_lo: float = 0.15
second_hi: float = 0.40
@dataclass(frozen=True)