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

11/18/2021
by   Hang Zhou, et al.
6

We propose SUB-Depth, a universal multi-task training framework for self-supervised monocular depth estimation (SDE). Depth models trained with SUB-Depth outperform the same models trained in a standard single-task SDE framework. By introducing an additional self-distillation task into a standard SDE training framework, SUB-Depth trains a depth network, not only to predict the depth map for an image reconstruction task, but also to distill knowledge from a trained teacher network with unlabelled data. To take advantage of this multi-task setting, we propose homoscedastic uncertainty formulations for each task to penalize areas likely to be affected by teacher network noise, or violate SDE assumptions. We present extensive evaluations on KITTI to demonstrate the improvements achieved by training a range of existing networks using the proposed framework, and we achieve state-of-the-art performance on this task. Additionally, SUB-Depth enables models to estimate uncertainty on depth output.

READ FULL TEXT

page 1

page 3

page 5

page 6

research
10/24/2021

X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation

In this paper, we propose a novel method, X-Distill, to improve the self...
research
05/13/2020

On the uncertainty of self-supervised monocular depth estimation

Self-supervised paradigms for monocular depth estimation are very appeal...
research
05/05/2022

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

In this paper, we deal with the problem of monocular depth estimation fo...
research
01/19/2023

SoftEnNet: Symbiotic Monocular Depth Estimation and Lumen Segmentation for Colonoscopy Endorobots

Colorectal cancer is the third most common cause of cancer death worldwi...
research
08/29/2019

Improving Self-Supervised Single View Depth Estimation by Masking Occlusion

Single view depth estimation models can be trained from video footage us...
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
06/20/2023

Self-supervised Multi-task Learning Framework for Safety and Health-Oriented Connected Driving Environment Perception using Onboard Camera

Cutting-edge connected vehicle (CV) technologies have drawn much attenti...

Please sign up or login with your details

Forgot password? Click here to reset