2020/04/13 by Robert McCraith, Lukas Neumann, Lukáš Neumann +6 · 2 citations
Computer Science · Engineering · #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Machine Learning (cs.LG) #Optical measurement and interference techniques #cs.CV #cs.LG
paper · pdf · doi:10.48550/arxiv.2004.05821
IROS submission, 7 pages
arxiv created 2020/04/13 · openalex publication_date 2020/04/13 · arxiv updated 2020/04/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics applications,multiple views of a scene may or may not be available, depend-ing on the actions of the robot, switching between monocularand multi-view reconstruction. To address this mixed setting,we proposed a new approach that extends any off-the-shelfself-supervised monocular depth reconstruction system to usemore than one image at test time. Our method builds on astandard prior learned to perform monocular reconstruction,but uses self-supervision at test time to further improve thereconstruction accuracy when multiple images are available.When used to update the correct components of the model, thisapproach is highly-effective. On the standard KITTI bench-mark, our self-supervised method consistently outperformsall the previous methods with an average 25% reduction inabsolute error for the three common setups (monocular, stereoand monocular+stereo), and comes very close in accuracy whencompared to the fully-supervised state-of-the-art methods.