αDepth：學習單次通過的軟邊界分解以進行立體轉換

摘要

準確建模軟邊界（例如毛髮與散景模糊）是立體轉換中的一項基本挑戰，原因在於前景與背景的模糊混合。現有的深度模型主要預測單層深度，導致軟邊界處深度對應關係的模糊性。雖然遮罩技術能捕捉透明度以進行分層建模，但在包含多個目標的複雜場景中常面臨困難，且通常需要使用者介入。本文介紹αDepth，一種可分解軟邊界以實現高保真立體轉換的分層表示法。具體而言，我們首先透過估算軟邊界處的分層色彩與深度值，解決混合色彩與深度的模糊性。考量複雜的多目標場景，我們設計了環形阿爾法表示法（Circular Alpha Representation, CAR），將範式從全域目標提取轉向局部邊界分解。不同於先前受限於單一前景/背景的遮罩方法，CAR無需手動引導即可實現高效的場景層級推論。廣泛的評估結果顯示，αDepth在立體轉換中達到最先進的效能，消除軟邊界處的背景滲色與結構失真。

English

Accurately modeling soft boundaries, e.g., hair and defocus blur, is a fundamental challenge in stereo conversion due to the ambiguous blending of foreground and background. Existing depth models primarily predict single-layer depth, leading to ambiguity in depth correspondence at soft boundaries. While matting techniques can capture opacity for layered modeling, they often struggle in complex scenes with multiple targets and usually require user intervention. This paper introduces αDepth, a layered representation that decomposes soft boundaries for high-fidelity stereo conversion. Specifically, we first resolve mixed color and depth ambiguity by estimating layered color and depth values at soft boundaries. Considering complex multi-target scenes, we design a Circular Alpha Representation (CAR) that shifts the paradigm from global target extraction to local boundary decomposition. Unlike prior matting methods restricted to a single foreground/background, CAR enables efficient scene-level inference without manual guidance. Extensive evaluations demonstrate that αDepth achieves state-of-the-art performance in stereo conversion, eliminating background bleeding and structural distortions at soft boundaries.