Saved in:
Bibliographic Details
Main Authors: Oei, Victor, Schmalfuss, Jenny, Mehl, Lukas, Bartsch, Madlen, Agnihotri, Shashank, Keuper, Margret, Bulling, Andreas, Bruhn, Andrés
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.09368
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908958566907904
author Oei, Victor
Schmalfuss, Jenny
Mehl, Lukas
Bartsch, Madlen
Agnihotri, Shashank
Keuper, Margret
Bulling, Andreas
Bruhn, Andrés
author_facet Oei, Victor
Schmalfuss, Jenny
Mehl, Lukas
Bartsch, Madlen
Agnihotri, Shashank
Keuper, Margret
Bulling, Andreas
Bruhn, Andrés
contents 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 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. It is available at https://spring-benchmark.org.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09368
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
Oei, Victor
Schmalfuss, Jenny
Mehl, Lukas
Bartsch, Madlen
Agnihotri, Shashank
Keuper, Margret
Bulling, Andreas
Bruhn, Andrés
Computer Vision and Pattern Recognition
Machine Learning
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 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. It is available at https://spring-benchmark.org.
title RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2505.09368