New paper accepted at ICLR

We are pleased to announce that the following paper was accepted at the International Conference on Learning Representations (ICLR).

Congratulations to the authors!

1. 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, Andrés Bruhn

   Proc. International Conference on Learning Representations (ICLR), 2026.

   Abstract Links BibTeX Project

   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 high-resolution 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 public 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 that treats robustness as a first-class citizen to foster models that combine accuracy with resilience.

   doi:

   @inproceedings{oei26_iclr, title = {{RobustSpring}: {Benchmarking} {Robustness} to {Image} {Corruptions} for {Optical} {Flow}, {Scene} {Flow} and {Stereo}}, shorttitle = {{RobustSpring}}, author = {Oei, Victor and Schmalfuss, Jenny and Mehl, Lukas and Bartsch, Madlen and Agnihotri, Shashank and Keuper, Margret and Bulling, Andreas and Bruhn, Andrés}, year = {2026}, doi = {}, booktitle = {Proc. International Conference on Learning Representations (ICLR)} }

Here are some related news you might like to read next:

• New paper accepted at IV Symposium
• New paper accepted at PETS
• New paper accepted at ECAI Workshop
• Two papers accepted at EMNLP
• New paper accepted in TMLR