Image Masking for Robust Self-Supervised Monocular Depth Estimation

10/05/2022
by   Hemang Chawla, et al.
10

Self-supervised monocular depth estimation is a salient task for 3D scene understanding. Learned jointly with monocular ego-motion estimation, several methods have been proposed to predict accurate pixel-wise depth without using labeled data. Nevertheless, these methods focus on improving performance under ideal conditions without natural or digital corruptions. A general absence of occlusions is assumed even for object-specific depth estimation. These methods are also vulnerable to adversarial attacks, which is a pertinent concern for their reliable deployment on robots and autonomous driving systems. We propose MIMDepth, a method that adapts masked image modeling (MIM) for self-supervised monocular depth estimation. While MIM has been used to learn generalizable features during pre-training, we show how it could be adapted for direct training of monocular depth estimation. Our experiments show that MIMDepth is more robust to noise, blur, weather conditions, digital artifacts, occlusions, as well as untargeted and targeted adversarial attacks.

READ FULL TEXT

page 2

page 5

research
02/07/2022

Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsics

The advent of autonomous driving and advanced driver assistance systems ...
research
01/31/2023

Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks

Monocular Depth Estimation (MDE) is a critical component in applications...
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...
research
07/17/2023

Self-supervised Monocular Depth Estimation: Let's Talk About The Weather

Current, self-supervised depth estimation architectures rely on clear an...
research
11/20/2019

Analysis of Deep Networks for Monocular Depth Estimation Through Adversarial Attacks with Proposal of a Defense Method

In this paper, we consider adversarial attacks against a system of monoc...
research
06/08/2022

Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Maps

Self-supervised monocular depth estimation has been a subject of intense...

Please sign up or login with your details

Forgot password? Click here to reset