Director of Research (if dissertation) or Advisor (if thesis)
Department of Study
Electrical & Computer Eng
Electrical & Computer Engr
Degree Granting Institution
University of Illinois at Urbana-Champaign
computer vision, deep learning, multi-view stereo, DeepMVS, pattern recognition, 3D reconstruction, depth estimation, machine learning, convolutional neural network
We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction. Taking an arbitrary number of posed images as input, we first produce a set of plane-sweep volumes and use the proposed DeepMVS network to predict high-quality disparity maps. The key contributions that enable these results are (1) supervised pretraining on a photorealistic synthetic dataset, (2) an effective method for aggregating information across a set of unordered images, and (3) integrating multi-layer feature activations from the pre-trained VGG-19 network. We validate the efficacy of DeepMVS using the ETH3D Benchmark. Our results show that DeepMVS compares favorably against state-of-the-art conventional MVS algorithms and other ConvNet based methods, particularly for near-textureless regions and thin structures.