Conditional Single-view Shape Generation for Multi-view Stereo Reconstruction

CVPR 2019 Yi WeiShaohui LiuWang ZhaoJiwen LuJie Zhou

In this paper, we present a new perspective towards image-based shape generation. Most existing deep learning based shape reconstruction methods employ a single-view deterministic model which is sometimes insufficient to determine a single groundtruth shape because the back part is occluded... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.