DeMoN: Depth and Motion Network for Learning Monocular Stereo

  • Published 2017


Our network is a chain of encoder-decoder networks. Figures 15 and 16 explain the details of the two encoderdecoders used in the bootstrap and iterative net part. Fig. 17 gives implementation details for the refinement net. The encoder-decoders for the bootstrap and iterative net use additional inputs which come from previous predictions. Some of these… (More)


20 Figures and Tables

Slides referencing similar topics