Image Masking for Robust Self-Supervised Monocular Depth Estimation

Chawla, Hemang; Kishaan, Jeeveswaran,; Zonooz, Bahram

doi:10.1109/icra48891.2023.10161373

Cited by 3 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods are basically inefficient in the meticulous characteristic of estimating depth and can be affected, which might hamper their reliability in the concerned applications. Hence, in "Image Masking for Robust Self-Supervised Monocular Depth Estimation" [136], a depth model, MIMDepth (Masked Image Modeling Depth network), is suggested, which takes up the concept of MIM for the self-supervised task by training the monocular depth network directly. Block wise masking being applied with a significantly low mask ratio solely to the depth network yields high robustness to corruptions, occlusions, and various adversarial threats.…”

Section: Self-supervised Monocular Modelsmentioning

confidence: 99%

Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review

Lahiri,

Ren,

Lin

2024

Vehicles

View full text Add to dashboard Cite

A lot of research has been conducted in recent years on stereo depth estimation techniques, taking the traditional approach to a new level such that it is in an appreciably good form for competing in the depth estimation market with other methods, despite its few demerits. Sufficient progress in accuracy and depth computation speed has manifested during the period. Over the years, stereo depth estimation has been provided with various training modes, such as supervised, self-supervised, and unsupervised, before deploying it for real-time performance. These modes are to be used depending on the application and/or the availability of datasets for training. Deep learning, on the other hand, has provided the stereo depth estimation methods with a new life to breathe in the form of enhanced accuracy and quality of images, attempting to successfully reduce the residual errors in stages in some of the methods. Furthermore, depth estimation from a single RGB image has been intricate since it is an ill-posed problem with a lack of geometric constraints and ambiguities. However, this monocular depth estimation has gained popularity in recent years due to the development in the field, with appreciable improvements in the accuracy of depth maps and optimization of computational time. The help is mostly due to the usage of CNNs (Convolutional Neural Networks) and other deep learning methods, which help augment the feature-extraction phenomenon for the process and enhance the quality of depth maps/accuracy of MDE (monocular depth estimation). Monocular depth estimation has seen improvements in many algorithms that can be deployed to give depth maps with better clarity and details around the edges and fine boundaries, which thus helps in delineating between thin structures. This paper reviews various recent deep learning-based stereo and monocular depth prediction techniques emphasizing the successes achieved so far, the challenges acquainted with them, and those that can be expected shortly.

show abstract

Section: Self-supervised Monocular Modelsmentioning

confidence: 99%

Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review

Lahiri,

Ren,

Lin

2024

Vehicles

View full text Add to dashboard Cite

show abstract

Discriminative-Guided Diffusion-Based Self-supervised Monocular Depth Estimation

Liu,

Zhang,

Zhu

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation

Guesmi,

Hanif,

Ouni

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Monocular depth estimation (MDE) is an important task in scene understanding, and significant improvements in its performance have been witnessed with the utilization of convolutional neural networks (CNNs). These models can now be deployed on edge devices, thanks to advancements in CNN optimization, enabling effective depth estimation in safety-critical and security-sensitive systems like robots, rovers, drones, and autonomous cars. However, CNNs used for MDE are susceptible to adversarial attacks, which can be exploited for malicious purposes by generating plausible images containing carefully crafted perturbations that distort the model's output. To assess the vulnerability of CNN-based depth prediction methods, recent studies have attempted to design adversarial patches specifically targeting MDE. However, these methods have not been powerful enough to fully deceive the vision system in a systemically threatening manner. Their impact is less effective, misleading the depth prediction of only certain parts within the overlapping region of the input image by using conspicuous and eye-catching patterns. In this paper, we investigate the vulnerability of MDE to adversarial patches. We propose a novel Stealthy Adversarial Attacks on MDE (SAAM) that compromises MDE by either corrupting the estimated distance or causing an object to seamlessly blend into its surroundings. Our experiments demonstrate that the designed stealthy patch successfully causes a CNN to misestimate the depth of objects. In fact, our proposed adversarial patch achieves a significant 60% depth error with 99% ratio of the affected region. Importantly, despite its adversarial nature, the patch maintains a naturalistic appearance, making it inconspicuous to human observers. We believe that this work sheds light on the threat of adversarial attacks in the context of MDE on edge devices. We hope it raises awareness within the community about the potential real-life harm of such attacks and encourages further research into developing more robust and adaptive defense mechanisms.

show abstract

Image Masking for Robust Self-Supervised Monocular Depth Estimation

Cited by 3 publications

References 20 publications

Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review

Deep Learning-Based Stereopsis and Monocular Depth Estimation Techniques: A Review

Discriminative-Guided Diffusion-Based Self-supervised Monocular Depth Estimation

SAAM: Stealthy Adversarial Attack on Monocular Depth Estimation

Contact Info

Product

Resources

About