MVSNet: Depth Inference for Unstructured Multi-view Stereo

TL;DR

MVSNet introduces a deep learning architecture for multi-view stereo depth inference that outperforms previous methods in accuracy and speed, demonstrating strong generalization across indoor and outdoor datasets.

Contribution

The paper presents a novel end-to-end deep learning framework for multi-view stereo depth estimation that is flexible, fast, and generalizes well without fine-tuning.

Findings

Outperforms previous state-of-the-art methods in accuracy.

Runs several times faster than existing approaches.

Achieves top ranking on outdoor datasets without fine-tuning.

Abstract

We present an end-to-end deep learning architecture for depth map inference from multi-view images. In the network, we first extract deep visual image features, and then build the 3D cost volume upon the reference camera frustum via the differentiable homography warping. Next, we apply 3D convolutions to regularize and regress the initial depth map, which is then refined with the reference image to generate the final output. Our framework flexibly adapts arbitrary N-view inputs using a variance-based cost metric that maps multiple features into one cost feature. The proposed MVSNet is demonstrated on the large-scale indoor DTU dataset. With simple post-processing, our method not only significantly outperforms previous state-of-the-arts, but also is several times faster in runtime. We also evaluate MVSNet on the complex outdoor Tanks and Temples dataset, where our method ranks first before April 18, 2018 without any fine-tuning, showing the strong generalization ability of MVSNet.