SuperMVS: Non-Uniform Cost Volume For High-Resolution Multi-View Stereo

TL;DR

SuperMVS introduces a non-uniform cost volume sampling method for multi-view stereo, reducing computational cost and improving depth accuracy in high-resolution 3D reconstruction.

Contribution

It proposes a dynamic, non-uniform hypothesis plane sampling technique and a coarse-to-fine network architecture for enhanced multi-view stereo performance.

Findings

Achieves state-of-the-art results on DTU and Tanks & Temples datasets.

Uses fewer hypothesis planes and less memory while maintaining high accuracy.

Reduces runtime compared to traditional uniform sampling methods.

Abstract

Different from most state-of-the-art~(SOTA) algorithms that use static and uniform sampling methods with a lot of hypothesis planes to get fine depth sampling. In this paper, we propose a free-moving hypothesis plane method for dynamic and non-uniform sampling in a wide depth range to build the cost volume, which not only greatly reduces the number of planes but also finers sampling, for both of reducing computational cost and improving accuracy, named Non-Uniform Cost Volume. We present the SuperMVS network to implement Multi-View Stereo with Non-Uniform Cost Volume. SuperMVS is a coarse-to-fine framework with four cascade stages. It can output higher resolution and accurate depth map. Our SuperMVS achieves the SOTA results with low memory, low runtime, and fewer planes on the DTU datasets and Tanks \& Temples dataset.