DeepMVS: Learning Multi-view Stereopsis

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 2821 - 2830
• Main Authors: Huang, Po-Han, Matzen, Kevin, Kopf, Johannes, Ahuja, Narendra, Huang, Jia-Bin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Calibration; Cameras; Decoding; Feature extraction; Image reconstruction; Semantics; Training

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 contribution...