PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Network

TL;DR

PVSNet introduces a pixelwise visibility-aware multi-view stereo network that learns visibility information to improve dense 3D reconstruction, especially under strong viewpoint variations, achieving state-of-the-art results.

Contribution

It is the first deep learning framework to explicitly learn pixelwise visibility information for multi-view stereo reconstruction.

Findings

Achieves state-of-the-art performance on multiple datasets.

Effectively handles datasets with strong viewpoint variations.

Demonstrates robustness through anti-noise training strategy.

Abstract

Recently, learning-based multi-view stereo methods have achieved promising results. However, they all overlook the visibility difference among different views, which leads to an indiscriminate multi-view similarity definition and greatly limits their performance on datasets with strong viewpoint variations. In this paper, a Pixelwise Visibility-aware multi-view Stereo Network (PVSNet) is proposed for robust dense 3D reconstruction. We present a pixelwise visibility network to learn the visibility information for different neighboring images before computing the multi-view similarity, and then construct an adaptive weighted cost volume with the visibility information. Moreover, we present an anti-noise training strategy that introduces disturbing views during model training to make the pixelwise visibility network more distinguishable to unrelated views, which is different with the existing learning methods that only use two best neighboring views for training. To the best of our knowledge, PVSNet is the first deep learning framework that is able to capture the visibility information of different neighboring views. In this way, our method can be generalized well to different types of datasets, especially the ETH3D high-res benchmark with strong viewpoint variations. Extensive experiments show that PVSNet achieves the state-of-the-art performance on different datasets.