# Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations

arXiv: https://arxiv.org/abs/2009.10142 · HTML: https://mlsanity.com/paper/2009.10142/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 19 of 19)

- [Not Just Streaks: Towards Ground Truth for Single Image Deraining](https://mlsanity.com/paper/2206.10779/) (2022)
- [Monitored Distillation for Positive Congruent Depth Completion](https://mlsanity.com/paper/2203.16034/) (2022)
- [RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions](https://mlsanity.com/paper/2410.02924/) (2024)
- [Stereoscopic Universal Perturbations across Different Architectures and Datasets](https://mlsanity.com/paper/2112.06116/) (2021)
- [A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow](https://mlsanity.com/paper/2203.13214/) (2022)
- [Towards Understanding Adversarial Robustness of Optical Flow Networks](https://mlsanity.com/paper/2103.16255/) (2021)
- [Distracting Downpour: Adversarial Weather Attacks for Motion Estimation](https://mlsanity.com/paper/2305.06716/) (2023)
- [AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation](https://mlsanity.com/paper/2310.09739/) (2023)
- [ProtoDepth: Unsupervised Continual Depth Completion with Prototypes](https://mlsanity.com/paper/2503.12745/) (2025)
- [Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens](https://mlsanity.com/paper/2508.04928/) (2025)
- [RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo](https://mlsanity.com/paper/2505.09368/) (2025)
- [ETA: Energy-based Test-time Adaptation for Depth Completion](https://mlsanity.com/paper/2508.05989/) (2025)
- [Towards Adversarially Robust and Domain Generalizable Stereo Matching by Rethinking DNN Feature Backbones](https://mlsanity.com/paper/2108.00335/) (2021)
- [Left-right Discrepancy for Adversarial Attack on Stereo Networks](https://mlsanity.com/paper/2401.07188/) (2024)
- [Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles](https://mlsanity.com/paper/2510.03224/) (2025)
- [Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep](https://mlsanity.com/paper/2401.12001/) (2024)
- [DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches](https://mlsanity.com/paper/2506.16690/) (2025)
- [Pixel-Optimization-Free Patch Attack on Stereo Depth Estimation](https://mlsanity.com/paper/2506.17632/) (2025)
- [Cheating Stereo Matching in Full-scale: Physical Adversarial Attack against Binocular Depth Estimation in Autonomous Driving](https://mlsanity.com/paper/2511.14386/) (2025)

## Abstract (arXiv)

We study the effect of adversarial perturbations of images on the estimates of disparity by deep learning models trained for stereo. We show that imperceptible additive perturbations can significantly alter the disparity map, and correspondingly the perceived geometry of the scene. These perturbations not only affect the specific model they are crafted for, but transfer to models with different architecture, trained with different loss functions. We show that, when used for adversarial data augmentation, our perturbations result in trained models that are more robust, without sacrificing overall accuracy of the model. This is unlike what has been observed in image classification, where adding the perturbed images to the training set makes the model less vulnerable to adversarial perturbations, but to the detriment of overall accuracy. We test our method using the most recent stereo networks and evaluate their performance on public benchmark datasets.