MMODELYST
Papers/αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
PAP

αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion

May 29, 2026

arXiv
Abstract

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.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Xiang Zhang, Yang Zhang, Lukas Mehl, Karlis Martins Briedis, Markus Gross, Christopher Schroers
Your notes (browser-local)
saved
Cross-links
No linked entities.
arXiv:2606.00386