Transactions on Machine Learning Research (TMLR) · 2026
Parameterized Adverse Lens Corruptions to Probe Model Robustness to Optical Tolerances
Why this publication matters
Small optical imperfections can matter to a vision model even when blur seems visually harmless. This work searches for difficult blur patterns through parameters tied to lens aberrations. That makes it possible to investigate robustness in terms of camera tolerances rather than arbitrary changes to image pixels.
Abstract
The original abstract will be added when the full paper is available.
Figures
Additional figures and captions will be added when the full paper is available.
Cite this paper
@article{bauerle2026parameterizedadverselens89,
title = {{Parameterized Adverse Lens Corruptions to Probe Model Robustness to Optical Tolerances}},
author = {K. Bäuerle and P. Müller and I. Ihrke and Margret Keuper},
journal = {Transactions on Machine Learning Research},
year = {2026},
url = {https://openreview.net/pdf?id=a93BmQRNxC}
}
Figures and abstract are reproduced from the linked research sources. Credit remains with the authors and publishers.