发表机构
Multimedia Laboratory, The Chinese University of Hong Kong; Adobe NextCam; Shanghai AI Laboratory; CPII under InnoHK（香港中文大学多媒体实验室; Adobe NextCam; 上海人工智能实验室; 创新香港研发平台下的CPII）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对图像抠图难题，提出视差人像抠图方法，利用连拍摄影中相机小幅度运动产生的前景-背景视差，通过估计trimap和前景/背景运动构建对齐视图预测，能恢复更精细细节和准确前景颜色。
AI 中文摘要
图像抠图是病态问题，在前景和背景纹理丰富时尤其困难。单图像抠图方法虽能从数据中学到强先验，但在复杂情况下表现不佳。现有方法需额外信号如绿幕、偏振光或干净背景图像来改善结果，且通常依赖特殊拍摄设置。我们提出视差人像抠图，一种实用的双帧抠图方法，利用轻微视角变化拍摄的第二张图像。此设置在连拍摄影中自然出现，相机小幅度运动产生前景-背景视差并为抠图提供补充观测。我们的流程估计trimap和前景/背景运动，构建对齐视图用于预测。为处理不完美的运动估计，网络使用背景对齐对直接融合，通过交叉注意力利用前景对齐线索进行误差补偿。实验表明，在具有挑战性的人像案例中，我们的方法比强大的单图像抠图基线能恢复更精细的细节和更准确的前景颜色。
英文摘要
Image matting is highly ill-posed, especially when both the foreground and background are richly textured. While single-image matting methods learn strong priors from data, they often struggle on these challenging cases. Existing approaches improve results by requiring additional signals such as green screens, polarized lighting, or clean background images, but these typically rely on specialized capture setups. We present Parallax Portrait Matting, a practical two-frame matting method that uses a second image captured with slight viewpoint change. Such a setting arises naturally in burst photography, where small camera motion induces foreground-background parallax and provides complementary observations for matting. Our pipeline estimates trimaps and foreground/background motion, then constructs aligned views for prediction. To handle imperfect motion estimation, the network uses the background-aligned pair for direct fusion and the foreground-aligned cue through cross-attention for error compensation. Experiments show that our method recovers finer details and more accurate foreground colors than strong single-image matting baselines on challenging portrait cases.
CommentsECCV 2026
