Learning deformable hypothesis sampling for patchmatch multi-view stereo in the wild

Yao Guo, Xianwei Zheng, Hongjie Li, Linxi Huan, Jiayi Ma, Jianya Gong

Abstract: Highlights•A DefLearn strategy is devised to enable scene-aware depth hypothesis sampling learning.•A PPMNet is proposed with DefLearn to address noisy depth estimation problem in the wild.•PPMNet achieves SOTA performance constantly in different challenging wild scenes.