FlowBench: A Robustness Benchmark for Optical Flow Estimation
Keywords: Adversarial attacks, optical flow estimation, benchmarking tool, benchmark, robustness
TL;DR: A robustness benchmarking tool and benchmark for optical flow estimation.
Abstract: Optical flow estimation is a crucial computer vision task often applied to safety-critical real-world scenarios like autonomous driving and medical imaging.
While optical flow estimation accuracy has greatly benefited from the emergence of deep learning, learning-based methods are also known for their lack of generalization and reliability.
However, reliability is paramount when optical flow methods are employed in the real world, where safety is essential.
Furthermore, a deeper understanding of the robustness and reliability of learning-based optical flow estimation methods is still lacking, hindering the research community from building methods safe for real-world deployment.
Thus we propose **FlowBench**, a robustness benchmark and evaluation tool for learning-based optical flow methods.
**FlowBench** facilitates streamlined research into the reliability of optical flow methods by benchmarking their robustness to adversarial attacks and out-of-distribution samples.
With **FlowBench**, we benchmark 91 methods across 3 different datasets under 7 diverse adversarial attacks and 23 established common corruptions, making it the most comprehensive robustness analysis of optical flow methods to date.
Across this wide range of methods, we consistently find that methods with state-of-the-art performance on established standard benchmarks lack reliability and generalization ability.
Moreover, we find interesting correlations between the performance, reliability, and generalization ability of optical flow estimation methods, under various lenses such as design choices used, number of parameters, etc.
After acceptance, **FlowBench** will be open-source and publicly available, including the weights of all tested models.
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 1055
Loading