Goto

Collaborating Authors

 consistency loss



Focus On What Matters: Separated Models For Visual-Based RL Generalization

Neural Information Processing Systems

Perceiving the pre-eminence of image reconstruction in representation learning, we propose SMG (Separated Models for Generalization), a novel approach that exploits image reconstruction for generalization.





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

Jiawang Bian, Zhichao Li, Naiyan Wang, Huangying Zhan, Chunhua Shen, Ming-Ming Cheng, Ian Reid

Neural Information Processing Systems

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.