no code implementations • 30 Aug 2019 • Yuchao Dai, Zhidong Zhu, Zhibo Rao, Bo Li
The success of existing deep-learning based multi-view stereo (MVS) approaches greatly depends on the availability of large-scale supervision in the form of dense depth maps.
no code implementations • 25 Apr 2019 • Zhidong Zhu, Mingyi He, Yuchao Dai, Zhibo Rao, Bo Li
The network consists of three modules: Multi-Scale 2D local feature extraction module, Cross-form spatial pyramid module and Multi-Scale 3D Feature Matching and Fusion module.
no code implementations • 25 Apr 2019 • Zhibo Rao, Mingyi He, Yuchao Dai, Zhidong Zhu, Bo Li, Renjie He
The multi-scale residual 3D convolution module learns the different scale geometry context from the cost volume which aggregated by the multi-scale fusion 2D convolution module.