CVLGApr 13, 2020

Monocular Depth Estimation with Self-supervised Instance Adaptation

arXiv:2004.05821v121 citations
Originality Incremental advance
AI Analysis

This addresses a practical challenge for robotics applications by improving depth reconstruction accuracy in mixed monocular and multi-view settings, though it is incremental as it builds on existing self-supervised methods.

The paper tackles the problem of monocular depth estimation in robotics where multiple views may or may not be available, by extending self-supervised methods to use multiple images at test time, resulting in a 25% reduction in absolute error on the KITTI benchmark.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes