Proceedings of the Nineth International Conference on Learning Representations (ICLR 26) · 2026

RobustSpring - Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo

Victor Oei, Jenny Schmalfuss, Lukas Mehl, Madlen Bartsch, Shashank Agnihotri, Margret Keuper, Andreas Bulling, Andres Bruhn

Why this publication matters

Motion and depth algorithms need tests in which visual changes remain consistent across frames and camera views. RobustSpring provides such corruptions instead of treating each image in isolation. It supports more realistic comparisons of how vision systems handle difficult conditions.

Abstract

Standard benchmarks for optical flow, scene flow, and stereo vision algorithms generally focus on model accuracy rather than robustness to image corruptions like noise or rain. Hence, the resilience of models to such real-world perturbations is largely unquantified. To address this, we present RobustSpring, a comprehensive dataset and benchmark for evaluating robustness to image corruptions for optical flow, scene flow, and stereo models. RobustSpring applies 20 different image corruptions, including noise, blur, color changes, quality degradations, and weather distortions, in a time-, stereo-, and depth-consistent manner to the highresolution Spring dataset, creating a suite of 20,000 corrupted images that reflect challenging conditions. RobustSpring enables comparisons of model robustness via a new corruption robustness metric. Integration with the Spring benchmark enables two-axis evaluations of both accuracy and robustness. We benchmark a curated selection of initial models, observing that robustness varies widely by corruption type, and experimentally show that evaluations on RobustSpring indicate real-world robustness. RobustSpring is a new computer vision benchmark to treat robustness as a first-class citizen, fostering models that are accurate and resilient.

Abstract source ↗

Figures

Consistent scene corruptions for optical-flow, stereo, and scene-flow evaluation. — **Figure 1.** RobustSpring is a novel image corruption benchmark for optical flow, scene flow, and stereo. It evaluates 20 image corruptions including blurs, color changes, noises, quality degradations, and weather, applied to stereo video data from Spring. For comprehensive robustness evaluations, RobustSpring’s image corruptions are integrated in time, stereo, and depth, where applicable. View in source ↗

**Figure 2.** Overview of RobustSpring’s image corruptions. View in source ↗

Cite this paper

Download .bib

@inproceedings{oei2026robustspringbenchmarkingrobustness80,
  title = {{RobustSpring - Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo}},
  author = {Victor Oei and Jenny Schmalfuss and Lukas Mehl and Madlen Bartsch and Shashank Agnihotri and Margret Keuper and Andreas Bulling and Andres Bruhn},
  booktitle = {International Conference on Learning Representations},
  year = {2026},
  url = {https://openreview.net/forum?id=RebPBMrMmk}
}

Figures and abstract are reproduced from the linked research sources. Credit remains with the authors and publishers.