Cost Volume Pyramid Network with Multi-strategies Range Searching for Multi-view Stereo

TL;DR

This paper introduces a novel multi-view stereo network that employs a cost volume pyramid with adaptive range searching strategies, improving depth estimation accuracy and efficiency over existing methods.

Contribution

It proposes a new cost volume pyramid network with different search strategies and adaptive filtering, enhancing depth estimation in multi-view stereo tasks.

Findings

Outperforms most state-of-the-art methods on DTU and BlendedMVS datasets.

Achieves more accurate depth estimation in low-resolution stages.

Effectively iterates upsampled depth maps to arbitrary resolutions.

Abstract

Multi-view stereo is an important research task in computer vision while still keeping challenging. In recent years, deep learning-based methods have shown superior performance on this task. Cost volume pyramid network-based methods which progressively refine depth map in coarse-to-fine manner, have yielded promising results while consuming less memory. However, these methods fail to take fully consideration of the characteristics of the cost volumes in each stage, leading to adopt similar range search strategies for each cost volume stage. In this work, we present a novel cost volume pyramid based network with different searching strategies for multi-view stereo. By choosing different depth range sampling strategies and applying adaptive unimodal filtering, we are able to obtain more accurate depth estimation in low resolution stages and iteratively upsample depth map to arbitrary resolution. We conducted extensive experiments on both DTU and BlendedMVS datasets, and results show that our method outperforms most state-of-the-art methods.