Author:
He Pengpeng,Wang Yueju,HU Yong,He Wei
Reference39 articles.
1. We compare the memory overhead of our method with those of several previous learning-based MVS methods [3-5,13] on DTU [11]. The memory usage evaluation is conducted with an image size of 1152 � 1600. Our ICV-Net uses the least memory capacity among all the methods. More specifically, the memory footprint is reduced by 87;Memory Overhead Comparison
2. Prior depth-based multi-view stereo network for online 3D model reconstruction;S Song;Pattern Recognition,2023
3. A multi-view stereo depth estimation network with adaptive depth range and depth interval;S Zhang;Pattern Recognition,2023
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献