DeepAI AI Chat
Log In Sign Up

Monocular Depth Estimation with Self-supervised Instance Adaptation

by   Robert McCraith, et al.

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.


FusionDepth: Complement Self-Supervised Monocular Depth Estimation with Cost Volume

Multi-view stereo depth estimation based on cost volume usually works be...

SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields

3D reconstruction from 2D image was extensively studied, training with d...

Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction

Despite recent advances in 3D human mesh reconstruction, domain gap betw...

SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images

Bird's-Eye-View (BEV) semantic maps have become an essential component o...

Self-supervised Learning of Motion Capture

Current state-of-the-art solutions for motion capture from a single came...

Learning what is above and what is below: horizon approach to monocular obstacle detection

A novel approach is proposed for monocular obstacle detection, which rel...

Self-supervised Learning for Dense Depth Estimation in Monocular Endoscopy

We present a self-supervised approach to training convolutional neural n...