EPP-MVSNet: Epipolar-assembling based Depth Prediction for Multi-view Stereo

• Published in: Proceedings / IEEE International Conference on Computer Vision pp. 5712 - 5720
• Main Authors: Ma, Xinjun, Gong, Yue, Wang, Qirui, Huang, Jingwei, Chen, Lei, Yu, Fan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2021
• Subjects: 3D from a single image and shape-from-x; 3D from multiview and other sensors; Costs; Efficient training and inference methods; Image resolution; Learning systems; Memory management; Redundancy; Refining; Stereo; Three-dimensional displays

In this paper, we proposed EPP-MVSNet, a novel deep learning network for 3D reconstruction from multi-view stereo (MVS). EPP-MVSNet can accurately aggregate features at high resolution to a limited cost volume with an optimal depth range, thus, leads to effective and efficient 3D construction. Disti...