提出αDepth模型，精准分解软边界实现高质量立体转换
αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
- 通过分层颜色与深度估计解决软边界模糊问题
- 在复杂多目标场景中实现无须人工干预的全局推理
- 显著减少背景渗色和结构失真，适合影视立体化应用
准确建模软边界（如头发、散焦模糊）是立体转换中的核心挑战，因前景与背景在边界处存在模糊混合。现有深度模型多预测单层深度，导致软边界处深度对应模糊；而传统抠图方法在多目标复杂场景中表现不佳，且常需人工干预。本文提出αDepth，一种分层表示方法，用于高保真立体转换。首先通过估计软边界处的分层颜色与深度值，解决颜色与深度混合模糊问题。针对复杂多目标场景，设计循环透明度表示（CAR），将范式从全局目标提取转为局部边界分解。相比以往仅支持单一前景/背景的抠图方法，CAR可实现无需人工引导的高效场景级推理。大量实验表明，αDepth在立体转换上达到当前最优性能，有效消除软边界处的背景渗色与结构失真。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。