FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras

05/05/2022
by   Qingan Yan, et al.
0

In this paper, we deal with the problem of monocular depth estimation for fisheye cameras in a self-supervised manner. A known issue of self-supervised depth estimation is that it suffers in low-light/over-exposure conditions and in large homogeneous regions. To tackle this issue, we propose a novel ordinal distillation loss that distills the ordinal information from a large teacher model. Such a teacher model, since having been trained on a large amount of diverse data, can capture the depth ordering information well, but lacks in preserving accurate scene geometry. Combined with self-supervised losses, we show that our model can not only generate reasonable depth maps in challenging environments but also better recover the scene geometry. We further leverage the fisheye cameras of an AR-Glasses device to collect an indoor dataset to facilitate evaluation.

READ FULL TEXT

page 1

page 3

page 8

page 9

page 10

research
04/14/2020

RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes

We present a generalised self-supervised learning approach for monocular...
research
12/04/2021

Toward Practical Self-Supervised Monocular Indoor Depth Estimation

The majority of self-supervised monocular depth estimation methods focus...
research
03/10/2022

SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning

Monocular depth estimation in the wild inherently predicts depth up to a...
research
02/20/2023

Self-Supervised Monocular Depth Estimation with Self-Reference Distillation and Disparity Offset Refinement

Monocular depth estimation plays a fundamental role in computer vision. ...
research
11/18/2021

SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation

We propose SUB-Depth, a universal multi-task training framework for self...
research
10/02/2022

Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problem

Self-supervised monocular depth estimation (MDE) models universally suff...
research
03/03/2021

Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation

Dense depth estimation is essential to scene-understanding for autonomou...

Please sign up or login with your details

Forgot password? Click here to reset