VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priors

TL;DR

This paper introduces VHS, a high-resolution stereo-matching technique that leverages visual hull priors and a hybrid correlation scheme to improve depth estimation efficiency and accuracy in volumetric capture systems.

Contribution

The method integrates visual hull priors with a hybrid sparse-dense correlation scheme and a memory-efficient training approach for high-resolution stereo matching.

Findings

Outperforms state-of-the-art stereo matching methods in accuracy.

Reduces memory usage during training on high-resolution data.

Demonstrates effective use of visual hull guidance in depth estimation.

Abstract

We present a stereo-matching method for depth estimation from high-resolution images using visual hulls as priors, and a memory-efficient technique for the correlation computation. Our method uses object masks extracted from supplementary views of the scene to guide the disparity estimation, effectively reducing the search space for matches. This approach is specifically tailored to stereo rigs in volumetric capture systems, where an accurate depth plays a key role in the downstream reconstruction task. To enable training and regression at high resolutions targeted by recent systems, our approach extends a sparse correlation computation into a hybrid sparse-dense scheme suitable for application in leading recurrent network architectures. We evaluate the performance-efficiency trade-off of our method compared to state-of-the-art methods, and demonstrate the efficacy of the visual hull guidance. In addition, we propose a training scheme for a further reduction of memory requirements during optimization, facilitating training on high-resolution data.