Codex
61 lines
1.9 KiB
Python
61 lines
1.9 KiB
Python
from __future__ import annotations
|
|
|
|
import numpy as np
|
|
|
|
from .deps import require_cv2
|
|
from .settings import TrimapSettings
|
|
|
|
|
|
def radius_from_ratio(shape: tuple[int, int], ratio: float, minimum: int) -> int:
|
|
return max(minimum, int(round(max(shape) * ratio)))
|
|
|
|
|
|
def elliptical_kernel(radius: int) -> np.ndarray:
|
|
cv2 = require_cv2()
|
|
size = radius * 2 + 1
|
|
return cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (size, size))
|
|
|
|
|
|
def generate_trimap(
|
|
bg_confidence: np.ndarray, settings: TrimapSettings
|
|
) -> tuple[np.ndarray, dict[str, int]]:
|
|
cv2 = require_cv2()
|
|
shape = bg_confidence.shape
|
|
unknown_radius = radius_from_ratio(
|
|
shape, settings.unknown_radius_ratio, settings.min_unknown_radius
|
|
)
|
|
fg_safe_radius = radius_from_ratio(
|
|
shape, settings.fg_safe_radius_ratio, settings.min_fg_safe_radius
|
|
)
|
|
|
|
sure_bg = bg_confidence >= settings.sure_bg_threshold
|
|
low_bg = bg_confidence <= settings.sure_fg_threshold
|
|
|
|
bg_u8 = sure_bg.astype(np.uint8)
|
|
unknown_band = cv2.dilate(bg_u8, elliptical_kernel(unknown_radius)).astype(bool)
|
|
fg_safe = ~cv2.dilate(bg_u8, elliptical_kernel(fg_safe_radius)).astype(bool)
|
|
sure_fg = low_bg & fg_safe
|
|
|
|
trimap = np.full(shape, 128, dtype=np.uint8)
|
|
trimap[sure_bg] = 0
|
|
trimap[sure_fg] = 255
|
|
|
|
# Keep a protective unknown band around all sure background, including holes.
|
|
trimap[unknown_band & ~sure_bg & ~sure_fg] = 128
|
|
|
|
stats = {
|
|
"sure_bg_pixels": int((trimap == 0).sum()),
|
|
"unknown_pixels": int((trimap == 128).sum()),
|
|
"sure_fg_pixels": int((trimap == 255).sum()),
|
|
"unknown_radius": int(unknown_radius),
|
|
"fg_safe_radius": int(fg_safe_radius),
|
|
}
|
|
return trimap, stats
|
|
|
|
|
|
def trimap_to_alpha_seed(trimap: np.ndarray, bg_confidence: np.ndarray) -> np.ndarray:
|
|
alpha = np.clip(1.0 - bg_confidence, 0.0, 1.0).astype(np.float32)
|
|
alpha[trimap == 0] = 0.0
|
|
alpha[trimap == 255] = 1.0
|
|
return alpha
|