Add non-flat background mode (--no-chroma / chroma.enabled: false)
No colour key at all: segmentation alone drives the trimap (mode forced to 'seg', whose chroma terms degrade to no-ops on a zero background- confidence map), ViTMatte still refines the unknown band at full resolution, and pymatting still estimates edge foreground colour. 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 fallback. Guards: requires segmentation.enabled and matting_method 'vitmatte' (clear errors otherwise); despill/foreground handle model=None. Validation: flat-background default path is bit-identical pre/post (alpha and RGB |D|max = 0 on TestImage3). On a known-alpha subject composited over a gradient+blotch background, recovered alpha scores MAE 0.0018 / IoU@0.5 0.993 (0.995 with --cross-check-as-seg); the same input correctly fails auto-detection in default mode. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
@@ -59,6 +59,19 @@ background-hued residual such as blue trapped between hair strands). Switch with
|
||||
`--trimap-mode seg` (topology only, no hue split) or `directional-hard-bg` (aggressive
|
||||
— hard-removes background-hued pixels; can eat cool/shadowed white cloth).
|
||||
|
||||
## Non-flat backgrounds
|
||||
|
||||
Pass `--no-chroma` (or `chroma.enabled: false`) to matte images whose background is
|
||||
**not** one flat colour — gradients, textures, scenes. There is no colour key in
|
||||
this mode: the segmentation mask alone drives the trimap (mode forced to `seg`),
|
||||
ViTMatte still refines the unknown band at full resolution, and pymatting still
|
||||
estimates edge foreground colour. Every colour-keyed stage is bypassed: background
|
||||
auto-detection, the directional hue split, chroma alpha suppression, despill, and
|
||||
the cross-check veto (with `--cross-check-as-seg` the second model still provides
|
||||
the segmentation mask). Requires the segmentation pipeline; quality then rests
|
||||
entirely on the segmenter's mask, so expect flat-background results to stay
|
||||
stronger on hair-level detail.
|
||||
|
||||
## Background colour
|
||||
|
||||
By default (`screen_color: null`) the background colour is **auto-detected** from the
|
||||
|
||||
@@ -23,6 +23,7 @@ def main(
|
||||
device: str | None = typer.Option(None, "--device"),
|
||||
precision: str | None = typer.Option(None, "--precision", help="Compute precision for all models (ViTMatte cast + BiRefNet autocast): fp32 (default) | bf16 (faster + halves matting activation memory; needs bf16-capable hardware, else falls back to fp32)"),
|
||||
screen_color: str | None = typer.Option(None, "--screen-color", help="Background colour prior as #RRGGBB (default: auto-detect the flat background colour)"),
|
||||
chroma: bool | None = typer.Option(None, "--chroma/--no-chroma", help="Colour-key the flat background (default: on). --no-chroma = non-flat background mode: segmentation alone drives the trimap; auto-detect, hue split, chroma suppression, despill and the cross-check veto are bypassed"),
|
||||
matting_method: str | None = typer.Option(None, "--matting-method"),
|
||||
fallback_to_chroma_alpha: bool | None = typer.Option(None, "--fallback-to-chroma-alpha/--no-fallback-to-chroma-alpha"),
|
||||
sure_bg_threshold: float | None = typer.Option(None, "--sure-bg-threshold", min=0.0, max=1.0),
|
||||
@@ -42,6 +43,7 @@ def main(
|
||||
device=device,
|
||||
precision=precision,
|
||||
screen_color=screen_color,
|
||||
chroma=chroma,
|
||||
matting_method=matting_method,
|
||||
fallback_to_chroma_alpha=fallback_to_chroma_alpha,
|
||||
sure_bg_threshold=sure_bg_threshold,
|
||||
|
||||
+4
-1
@@ -99,6 +99,9 @@ def override_settings(settings: PipelineSettings, **overrides: Any) -> PipelineS
|
||||
}
|
||||
if overrides.get("trimap_mode") is not None:
|
||||
trimap_updates["mode"] = overrides["trimap_mode"]
|
||||
chroma_updates: dict[str, Any] = {}
|
||||
if overrides.get("chroma") is not None:
|
||||
chroma_updates["enabled"] = overrides["chroma"]
|
||||
despill_updates: dict[str, Any] = {}
|
||||
if overrides.get("despill") is not None:
|
||||
despill_updates["enabled"] = overrides["despill"]
|
||||
@@ -130,7 +133,7 @@ def override_settings(settings: PipelineSettings, **overrides: Any) -> PipelineS
|
||||
else settings.screen_color
|
||||
)
|
||||
return PipelineSettings(
|
||||
chroma=chroma,
|
||||
chroma=_update_dataclass(chroma, chroma_updates),
|
||||
trimap=_update_dataclass(trimap, trimap_updates),
|
||||
alpha_post=alpha_post,
|
||||
cross_check=_update_dataclass(settings.cross_check, cross_check_updates),
|
||||
|
||||
+3
-2
@@ -10,7 +10,7 @@ from .settings import DespillSettings
|
||||
def despill(
|
||||
rgb: np.ndarray,
|
||||
alpha: np.ndarray,
|
||||
model: BackgroundModel,
|
||||
model: BackgroundModel | None,
|
||||
settings: DespillSettings,
|
||||
) -> tuple[np.ndarray, np.ndarray]:
|
||||
"""Remove background-colour spill from the foreground.
|
||||
@@ -24,7 +24,8 @@ def despill(
|
||||
|
||||
Returns the corrected RGB (uint8) and the per-pixel despill weight (float32).
|
||||
"""
|
||||
if not settings.enabled:
|
||||
# model is None with chroma disabled: no key colour means no spill direction.
|
||||
if not settings.enabled or model is None:
|
||||
return rgb.copy(), np.zeros(alpha.shape, dtype=np.float32)
|
||||
|
||||
bg_lab = np.asarray(model.lab_center, dtype=np.float32)
|
||||
|
||||
@@ -11,7 +11,7 @@ def estimate_foreground_rgb(
|
||||
rgb: np.ndarray,
|
||||
alpha: np.ndarray,
|
||||
bg_confidence: np.ndarray,
|
||||
model: BackgroundModel,
|
||||
model: BackgroundModel | None,
|
||||
settings: ForegroundSettings,
|
||||
) -> np.ndarray:
|
||||
"""Estimated foreground colour F (uint8 HxWx3) for compositing over alpha."""
|
||||
@@ -23,10 +23,15 @@ def estimate_foreground_rgb(
|
||||
try:
|
||||
return _estimate_ml(rgb, alpha, settings)
|
||||
except RuntimeError:
|
||||
if not settings.fallback_to_unmix:
|
||||
if not settings.fallback_to_unmix or model is None:
|
||||
raise
|
||||
method = "unmix"
|
||||
if method == "unmix":
|
||||
if model is None:
|
||||
raise RuntimeError(
|
||||
"Foreground method 'unmix' needs the chroma background model, which "
|
||||
"does not exist with chroma disabled; use method 'ml'."
|
||||
)
|
||||
return _estimate_unmix(rgb, alpha, bg_confidence, model, settings)
|
||||
raise RuntimeError(
|
||||
f"Unsupported foreground method '{settings.method}'. Use 'ml' or 'unmix'."
|
||||
|
||||
+34
-13
@@ -132,10 +132,26 @@ def run_image(
|
||||
|
||||
def _process_rgb(rgb: np.ndarray, pipeline: MattingPipeline) -> MattingResult:
|
||||
settings = pipeline.settings
|
||||
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
|
||||
)
|
||||
if settings.chroma.enabled:
|
||||
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
|
||||
)
|
||||
else:
|
||||
if not settings.segmentation.enabled:
|
||||
raise RuntimeError(
|
||||
"chroma.enabled: false (non-flat background mode) needs the segmentation "
|
||||
"pipeline; enable segmentation or re-enable chroma."
|
||||
)
|
||||
if settings.model.matting_method == "chroma":
|
||||
raise RuntimeError(
|
||||
"matting_method 'chroma' needs the chroma key; use 'vitmatte' or re-enable chroma."
|
||||
)
|
||||
# Non-flat background: no colour key exists. A zero background-confidence
|
||||
# map makes every chroma-fused formula degrade to its seg-only form; the
|
||||
# colour-keyed stages (hue split, suppression, veto, despill) are skipped.
|
||||
bg_confidence = np.zeros(rgb.shape[:2], dtype=np.float32)
|
||||
model = None
|
||||
second_alpha = None
|
||||
if settings.segmentation.enabled:
|
||||
reuse = (
|
||||
@@ -154,7 +170,9 @@ def _process_rgb(rgb: np.ndarray, pipeline: MattingPipeline) -> MattingResult:
|
||||
seg_mask = second_alpha
|
||||
else:
|
||||
seg_mask = pipeline._segment(rgb)
|
||||
mode = settings.trimap.mode
|
||||
# The directional modes are colour tests against the key colour; without
|
||||
# one, the seg-topology trimap is the only meaningful choice.
|
||||
mode = settings.trimap.mode if settings.chroma.enabled else "seg"
|
||||
if mode == "seg":
|
||||
trimap, trimap_stats = fuse_trimap(seg_mask, bg_confidence, settings.trimap)
|
||||
elif mode in ("directional", "directional-hard-bg"):
|
||||
@@ -173,14 +191,17 @@ def _process_rgb(rgb: np.ndarray, pipeline: MattingPipeline) -> MattingResult:
|
||||
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,
|
||||
)
|
||||
if settings.chroma.enabled:
|
||||
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:
|
||||
# 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:
|
||||
lab = convert_color_spaces(rgb)[1]
|
||||
if second_alpha is None:
|
||||
second_alpha = pipeline._second_opinion(rgb)
|
||||
@@ -199,7 +220,7 @@ def _process_rgb(rgb: np.ndarray, pipeline: MattingPipeline) -> MattingResult:
|
||||
|
||||
metadata = {
|
||||
"alpha_source": alpha_source,
|
||||
"background_model": model.to_dict(),
|
||||
"background_model": model.to_dict() if model is not None else None,
|
||||
"trimap": trimap_stats,
|
||||
"settings": asdict(settings),
|
||||
}
|
||||
|
||||
@@ -5,6 +5,14 @@ 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'.
|
||||
enabled: bool = True
|
||||
border_ratio: float = 0.04
|
||||
min_samples: int = 2048
|
||||
lab_sigma_min: float = 10.0
|
||||
|
||||
@@ -3,6 +3,13 @@
|
||||
# like "#CFEFFF" sets it explicitly. Also overridable via --screen-color.
|
||||
screen_color: null
|
||||
|
||||
chroma:
|
||||
# false = non-flat background mode (--no-chroma): no colour key; segmentation
|
||||
# alone drives the trimap (mode forced to "seg") and every colour-keyed stage
|
||||
# is bypassed (auto-detect, hue split, chroma suppression, despill, the
|
||||
# cross-check veto). Needs segmentation.enabled and matting_method vitmatte.
|
||||
enabled: true
|
||||
|
||||
model:
|
||||
model_name: hustvl/vitmatte-base-composition-1k
|
||||
device: cpu
|
||||
|
||||
Reference in New Issue
Block a user