Monocular Depth Estimation with Self-supervised Instance Adaptation

Abstract

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.

IROS submission, 7 pages

References in corpus (9)

• From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
• Deep Ordinal Regression Network for Monocular Depth Estimation
• Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency
• Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction
• Learning Monocular Depth by Distilling Cross-domain Stereo Networks
• Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding
• LEGO: Learning Edge with Geometry all at Once by Watching Videos
• Single View Stereo Matching
• Learning monocular depth estimation with unsupervised trinocular assumptions

Cited by in corpus (6)

• DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume
• CoVIO: Online Continual Learning for Visual-Inertial Odometry
• CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation
• On the Coupling of Depth and Egomotion Networks for Self-Supervised Structure from Motion
• Instance-aware multi-object self-supervision for monocular depth prediction
• Calibrating Self-supervised Monocular Depth Estimation