e61fbe84f0
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>
129 lines
5.8 KiB
YAML
129 lines
5.8 KiB
YAML
# Background-colour prior. null = auto-detect the flat background colour from the
|
|
# image border (raises if the border is not one clean flat colour). A hex string
|
|
# 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
|
|
matting_method: vitmatte
|
|
fallback_to_chroma_alpha: false
|
|
# "bf16" halves ViTMatte activation memory and is ~3x faster on native-bf16
|
|
# CPUs (visually identical alpha); needs bf16-capable hardware (modern GPU /
|
|
# AVX512-BF16 CPU), else falls back to fp32. --precision bf16 sets bf16 here
|
|
# AND on the BiRefNet models below in one go.
|
|
precision: fp32
|
|
# Query-chunked global attention (exact, bitwise-identical output): caps the
|
|
# VitDet global blocks' N^2 attention transient at O(N * chunk) — 19.8 -> 4.0
|
|
# GB at 2048x2048 for ~15% more ViTMatte time. 0 = stock one-shot attention.
|
|
attn_query_chunk: 2048
|
|
|
|
segmentation:
|
|
# enabled: true = single-segmenter pipeline (one seg model drives the trimap)
|
|
# enabled: false = no seg model, chroma-only pipeline (Chroma + ViTMatte)
|
|
enabled: true
|
|
backend: birefnet # single trimap segmenter; switchable at runtime: --seg-backend birefnet|anime-seg
|
|
model_name: ZhengPeng7/BiRefNet # matches backend; --seg-backend anime-seg auto-selects skytnt/anime-seg
|
|
device: cpu
|
|
input_size: 1024
|
|
# BiRefNet forward precision: "bf16" runs via autocast (~1.4x on native-bf16
|
|
# CPUs, visually identical), else falls back to fp32. anime-seg ignores this.
|
|
precision: fp32
|
|
|
|
trimap:
|
|
sure_bg_threshold: 0.92
|
|
sure_fg_threshold: 0.12
|
|
unknown_radius_ratio: 0.012
|
|
fg_safe_radius_ratio: 0.006
|
|
seg_core_threshold: 0.60
|
|
seg_loose_threshold: 0.08
|
|
# Trimap mode (segmentation pipeline only; also settable via --trimap-mode):
|
|
# directional = chroma + seg + hue split; background-hued residual
|
|
# (blue between hair) -> unknown, white shirt kept. (default)
|
|
# seg = original fuse_trimap (no hue split).
|
|
# directional-hard-bg = hard-remove background-hued pixels (aggressive; can eat
|
|
# cool/shadowed white cloth).
|
|
mode: directional
|
|
seg_low: 0.15
|
|
bg_hue_proj_min: 4.0
|
|
# Semantic override (directional mode): chroma-unknown pixels with seg confidence
|
|
# at/above this stay sure-FG even when background-hued — rescues bright skin on a
|
|
# warm (same-hue-family) background that the hue split would otherwise hand to
|
|
# ViTMatte/suppression, which misfire exactly there. Never overrides chroma
|
|
# sure-background. Set > 1.0 to disable.
|
|
seg_force_fg: 0.98
|
|
|
|
alpha_post:
|
|
chroma_suppress: true
|
|
chroma_suppress_bg_low: 0.35
|
|
chroma_suppress_bg_high: 0.80
|
|
chroma_suppress_strength: 1.0
|
|
# Matte-confidence gate: suppression fades where ViTMatte's raw alpha is high
|
|
# (ramp lo -> hi), so colour evidence only vetoes the matte where it is unsure.
|
|
# Set suppress_raw_lo: 1.0 to disable.
|
|
suppress_raw_lo: 0.85
|
|
suppress_raw_hi: 0.98
|
|
|
|
cross_check:
|
|
# Cross-model veto: a second, trimap-free matting model may only LOWER alpha
|
|
# (min-fusion), only on background-hued bright pixels the primary result is
|
|
# confident about — clears colour-drifted background residue between hair
|
|
# strands that chroma, segmentation and ViTMatte all read as foreground.
|
|
# Costs one extra model (~0.9 GB download) and one inference pass per image.
|
|
# Disable with enabled: false or --no-cross-check.
|
|
enabled: true
|
|
model_name: ZhengPeng7/BiRefNet_HR-matting
|
|
input_size: 2048
|
|
# Reuse the cross-check forward as the seg mask: one HR-matting inference
|
|
# drives both trimap topology and the veto, skipping the primary seg model
|
|
# (saves its ~9s forward + ~0.9 GB load; CPU pipeline ~66s -> ~45s). Pilot:
|
|
# trimap 99.8% identical, no structural change (fingers/wisps/bowstring OK).
|
|
# Only applies to the birefnet backend (same-family swap); anime-seg keeps
|
|
# its own forward, with the cross-check running independently on top.
|
|
# Default OFF (server-edition): the dedicated segmenter keeps its own forward
|
|
# and the veto stays independent; enable with --cross-check-as-seg.
|
|
reuse_as_seg: false
|
|
# Cross-check forward precision, same semantics as segmentation.precision
|
|
# (bf16 via autocast: 2048 pass ~35s -> ~26s on a native-bf16 CPU).
|
|
precision: fp32
|
|
proj_min: 3.0 # bg-hue projection above which a pixel is suspect
|
|
l_min: 45.0 # Lab lightness below which a pixel is exempt (dark hair)
|
|
feather_sigma: 2.0 # zone-boundary feather, px
|
|
gate_lo: 0.70 # primary alpha below this -> fully exempt
|
|
gate_hi: 0.95 # primary alpha above this -> fully vetoable
|
|
|
|
foreground:
|
|
enabled: true
|
|
method: ml
|
|
fallback_to_unmix: true
|
|
ml_regularization: 0.00001
|
|
# Legacy "unmix" method params (used only when method: unmix).
|
|
edge_low: 0.005
|
|
edge_high: 0.995
|
|
min_unmix_alpha: 0.08
|
|
unmix_strength: 0.70
|
|
local_strength: 0.45
|
|
local_blur_radius: 11
|
|
local_alpha_threshold: 0.92
|
|
local_bg_confidence_max: 0.20
|
|
green_excess_margin: 0.015
|
|
bg_confidence_weight: 0.70
|
|
|
|
despill:
|
|
# Off: despill has no positional/semantic guard, so a subject sharing the
|
|
# background's hue (blue suit on a blue backdrop) gets desaturated/hue-shifted
|
|
# (~ΔE 35, blue -> purple). Re-enable per-job only when edge spill matters.
|
|
enabled: false
|
|
edge_low: 0.005
|
|
strength: 0.92
|
|
edge_expand_radius: 2
|
|
alpha_weight_floor: 0.35
|
|
color_margin_lab: 4.0 # Lab chroma margin along the background-colour direction
|