MVSNet: Depth Inference for Unstructured Multi-view Stereo

ECCV 2018  ·  Yao Yao, Zixin Luo, Shiwei Li, Tian Fang, Long Quan ·

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.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Results from the Paper

Ranked #19 on Point Clouds on Tanks and Temples (Mean F1 (Intermediate) metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Reconstruction DTU MVSNet Acc 0.396 # 19
Overall 0.462 # 20
Comp 0.527 # 20
Point Clouds Tanks and Temples MVSNet Mean F1 (Intermediate) 43.48 # 19


No methods listed for this paper. Add relevant methods here