文件名称：多视角几何重建网络RMVS
文件大小：4.67MB
文件格式：PDF
更新时间：2022-12-14 06:33:49
mvs
Deep learning has recently demonstrated its excellent performance for multi-view stereo (MVS). However, one major limitation of current learned MVS approaches is the scalability: thememory-consumingcostvolumeregularization makes the learned MVS hard to be applied to highresolution scenes. In this paper, we introduce a scalable multi-view stereo framework based on the recurrent neural network. Instead of regularizing the entire 3D cost volume in one go, the proposed Recurrent Multi-view Stereo Ne