"""CPU-conscious, conservative alpha enhancement for Remova images and video. Does not hallucinate missing objects; preserves high-confidence foreground and avoids processing every frame with a second neural network. """ import cv2 import numpy as np from PIL import Image def enhance_rgba(result: Image.Image, source: Image.Image, model: str = 'silueta', video: bool = False) -> Image.Image: """Edge-aware refinement restricted to uncertain alpha pixels.""" rgba = np.asarray(result.convert('RGBA')).copy() alpha = rgba[:, :, 3].copy() if alpha.size < 64 or alpha.max() < 8 or alpha.min() > 247: return result guide = np.asarray(source.convert('RGB')) if guide.shape[:2] != alpha.shape: guide = cv2.resize(guide, (alpha.shape[1], alpha.shape[0]), interpolation=cv2.INTER_AREA) # A one-channel guided filter avoids colour-channel covariance artifacts. gray = cv2.cvtColor(guide, cv2.COLOR_RGB2GRAY).astype(np.float32) / 255.0 p = alpha.astype(np.float32) / 255.0 radius = 3 if video else 4 kernel = (radius * 2 + 1, radius * 2 + 1) mean_i = cv2.boxFilter(gray, -1, kernel, normalize=True) mean_p = cv2.boxFilter(p, -1, kernel, normalize=True) cov = cv2.boxFilter(gray * p, -1, kernel, normalize=True) - mean_i * mean_p var = cv2.boxFilter(gray * gray, -1, kernel, normalize=True) - mean_i * mean_i a = cov / (var + 0.002) b = mean_p - a * mean_i refined = cv2.boxFilter(a, -1, kernel) * gray + cv2.boxFilter(b, -1, kernel) refined = np.clip(refined, 0, 1) # Only adjust the uncertain band. Do not erode hair or opaque body regions. uncertain = (alpha > 12) & (alpha < 243) strength = 0.42 if model == 'silueta' else 0.32 if video: strength *= 0.8 output = p.copy() output[uncertain] = (1 - strength) * p[uncertain] + strength * refined[uncertain] # Tiny isolated hard-mask speckles can be removed only when sufficiently # far from any substantial component. Keep multi-object subjects intact. if not video: core = (alpha >= 200).astype(np.uint8) count, labels, stats, _ = cv2.connectedComponentsWithStats(core, 8) if count > 2: large = np.zeros_like(core) threshold = max(16, int(alpha.size * 0.00008)) for i in range(1, count): if stats[i, cv2.CC_STAT_AREA] >= threshold: large[labels == i] = 1 if large.any(): near = cv2.dilate(large, np.ones((7, 7), np.uint8)) for i in range(1, count): if stats[i, cv2.CC_STAT_AREA] < threshold: component = labels == i if not np.any(near & component): output[component] = 0 rgba[:, :, 3] = np.uint8(np.clip(output * 255 + 0.5, 0, 255)) return Image.fromarray(rgba, 'RGBA')