mlsanityData to 7 Oct 2026

Targeted Adversarial Perturbations for Monocular Depth Prediction

arXiv 2006.08602 ↗First posted 12 Jun 2020cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

We study the effect of adversarial perturbations on the task of monocular depth prediction. Specifically, we explore the ability of small, imperceptible additive perturbations to selectively alter the perceived geometry of the scene. We show that such perturbations can not only globally re-scale the predicted distances from the camera, but also alter the prediction to match a different target scene. We also show that, when given semantic or instance information, perturbations can fool the network to alter the depth of specific categories or instances in the scene, and even remove them while preserving the rest of the scene. To understand the effect of targeted perturbations, we conduct experiments on state-of-the-art monocular depth prediction methods. Our experiments reveal vulnerabilities in monocular depth prediction networks, and shed light on the biases and context learned by them.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 6; 2023: 5; 2024: 10; 2025: 10; 2026: 2.

40 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  3. 2021Learning Topology from Synthetic Data for Unsupervised Depth Completioncited by 38
  4. 2024WorDepth: Variational Language Prior for Monocular Depth Estimationcited by 34
  5. 2024Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Drivingcited by 32
  6. 2022Not Just Streaks: Towards Ground Truth for Single Image Derainingcited by 31
  7. 2021An Adaptive Framework for Learning Unsupervised Depth Completioncited by 30
  8. 2023CosPGD: an efficient white-box adversarial attack for pixel-wise prediction taskscited by 27
  9. 2022Monitored Distillation for Positive Congruent Depth Completioncited by 24
  10. 2024RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptionscited by 20
  11. 2022Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsicscited by 19
  12. 2021Stereoscopic Universal Perturbations across Different Architectures and Datasetscited by 17
28 more
  1. 2023Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attackscited by 17
  2. 2023AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimationcited by 15
  3. 2025ProtoDepth: Unsupervised Continual Depth Completion with Prototypescited by 11
  4. 2023APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigationcited by 10
  5. 2025Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokenscited by 9
  6. 2021UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attackscited by 7
  7. 2022Adversarial Attacks on Monocular Pose Estimationcited by 6
  8. 2022Image Masking for Robust Self-Supervised Monocular Depth Estimationcited by 5
  9. 2024Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attackscited by 5
  10. 2024Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Taskscited by 5
  11. 2021Consistent Semantic Attacks on Optical Flowcited by 4
  12. 2024SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applicationscited by 4
  13. 2025ETA: Energy-based Test-time Adaptation for Depth Completioncited by 4
  14. 2024Optical Lens Attack on Deep Learning Based Monocular Depth Estimationcited by 3
  15. 2024Left-right Discrepancy for Adversarial Attack on Stereo Networkscited by 2
  16. 2021Learning-Based Vulnerability Analysis of Cyber-Physical Systemscited by 1
  17. 2025TR2M: Transferring Monocular Relative Depth to Metric Depth with Language Descriptions and Dual-Level Scale-Oriented Contrastcited by 1
  18. 2025Guided Diffusion-based Generation of Adversarial Objects for Real-World Monocular Depth Estimation Attackscited by 1
  19. 2023Transformers in Unsupervised Structure-from-Motioncited by 0
  20. 2024Physical Adversarial Attack on Monocular Depth Estimation via Shape-Varying Patchescited by 0
  21. 2024Optical Lens Attack on Monocular Depth Estimation for Autonomous Drivingcited by 0
  22. 2025VGLD: Visually-Guided Linguistic Disambiguation for Monocular Depth Scale Recoverycited by 0
  23. 2025DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patchescited by 0
  24. 2025Pixel-Optimization-Free Patch Attack on Stereo Depth Estimationcited by 0
  25. 2025BiTAA: A Bi-Task Adversarial Attack for Object Detection and Depth Estimation via 3D Gaussian Splattingcited by 0
  26. 2025The 3D Mirage: Probing and Taming 3D Hallucinationscited by 0
  27. 2026RACF: A Resilient Autonomous Car Framework with Object Distance Correctioncited by 0
  28. 2026Efficient Semantic Understanding from Digital Foveationcited by 0