Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video

28 Aug 2019Jia-Wang BianZhichao LiNaiyan WangHuangying ZhanChunhua ShenMing-Ming ChengIan Reid

Recent work has shown that CNN-based depth and ego-motion estimators can be learned using unlabelled monocular videos. However, the performance is limited by unidentified moving objects that violate the underlying static scene assumption in geometric image reconstruction... (read more)

PDF Abstract

Evaluation results from the paper

#13 best model for Monocular Depth Estimation on KITTI Eigen split (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Monocular Depth Estimation KITTI Eigen split SC-SfMLearner absolute relative error 0.137 # 16
Monocular Depth Estimation KITTI Eigen split SC-SfMLearner_CS+K absolute relative error 0.128 # 13