DeMoN: Depth and Motion Network for Learning Monocular Stereo

CVPR 2017 Benjamin UmmenhoferHuizhong ZhouJonas UhrigNikolaus MayerEddy IlgAlexey DosovitskiyThomas Brox

In this paper we formulate structure from motion as a learning problem. We train a convolutional network end-to-end to compute depth and camera motion from successive, unconstrained image pairs... (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.