MVSNet: Depth Inference for Unstructured Multi-view Stereo
This addresses the problem of efficient and accurate 3D reconstruction from images for computer vision applications, representing a strong specific gain rather than a broad paradigm shift.
The paper tackles depth map inference from multi-view images by introducing MVSNet, an end-to-end deep learning architecture that significantly outperforms previous state-of-the-art methods on the DTU dataset and ranks first on the Tanks and Temples dataset without fine-tuning, while being several times faster in runtime.
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.