Learning Single-View 3D Reconstruction with Limited Pose Supervision

ECCV 2018 Guandao YangYin CuiSerge BelongieBharath Hariharan

It is expensive to label images with 3D structure or precise camera pose. Yet, this is precisely the kind of annotation required to train single-view 3D reconstruction models... (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.