Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching

arXiv:2403.10755v1 Announce Type: new
Abstract: Dynamic stereo matching is the task of estimating consistent disparities from stereo videos with dynamic objects. Recent learning-based methods prioritize optimal performance on a single stereo pair, resulting in temporal inconsistencies. Existing video methods apply per-frame matching and window-based cost aggregation across the time dimension, leading to low-frequency oscillations at the scale of the window size. Towards this challenge, we develop a bidirectional alignment mechanism for adjacent frames as a fundamental operation. We further propose …

abstract aggregation alignment apply arxiv consistent cost cs.cv dynamic match objects per performance temporal type video videos