Learn to Adapt for Monocular Depth Estimation

03/26/2022
by   Qiyu Sun, et al.
0

Monocular depth estimation is one of the fundamental tasks in environmental perception and has achieved tremendous progress in virtue of deep learning. However, the performance of trained models tends to degrade or deteriorate when employed on other new datasets due to the gap between different datasets. Though some methods utilize domain adaptation technologies to jointly train different domains and narrow the gap between them, the trained models cannot generalize to new domains that are not involved in training. To boost the transferability of depth estimation models, we propose an adversarial depth estimation task and train the model in the pipeline of meta-learning. Our proposed adversarial task mitigates the issue of meta-overfitting, since the network is trained in an adversarial manner and aims to extract domain invariant representations. In addition, we propose a constraint to impose upon cross-task depth consistency to compel the depth estimation to be identical in different adversarial tasks, which improves the performance of our method and smoothens the training process. Experiments demonstrate that our method adapts well to new datasets after few training steps during the test procedure.

READ FULL TEXT

page 1

page 5

page 6

page 8

page 9

research
04/12/2021

Domain Adaptive Monocular Depth Estimation With Semantic Information

The advent of deep learning has brought an impressive advance to monocul...
research
03/05/2018

AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation

Supervised deep learning methods have shown promising results for the ta...
research
09/03/2020

DESC: Domain Adaptation for Depth Estimation via Semantic Consistency

Accurate real depth annotations are difficult to acquire, needing the us...
research
09/24/2021

Adversarial Domain Feature Adaptation for Bronchoscopic Depth Estimation

Depth estimation from monocular images is an important task in localizat...
research
05/28/2020

Monocular Depth Estimators: Vulnerabilities and Attacks

Recent advancements of neural networks lead to reliable monocular depth ...
research
03/08/2023

Aberration-Aware Depth-from-Focus

Computer vision methods for depth estimation usually use simple camera m...
research
07/30/2022

Learning Feature Decomposition for Domain Adaptive Monocular Depth Estimation

Monocular depth estimation (MDE) has attracted intense study due to its ...

Please sign up or login with your details

Forgot password? Click here to reset