OmniLens++: Blind Lens Aberration Correction via Large LensLib Pre-Training and Latent PSF Representation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jiang, Qi, Qian, Xiaolong, Gao, Yao, Sun, Lei, Yang, Kailun, Yi, Zhonghua, Li, Wenyong, Yang, Ming-Hsuan, Van Gool, Luc, Wang, Kaiwei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915636377026560
author Jiang, Qi
Qian, Xiaolong
Gao, Yao
Sun, Lei
Yang, Kailun
Yi, Zhonghua
Li, Wenyong
Yang, Ming-Hsuan
Van Gool, Luc
Wang, Kaiwei
author_facet Jiang, Qi
Qian, Xiaolong
Gao, Yao
Sun, Lei
Yang, Kailun
Yi, Zhonghua
Li, Wenyong
Yang, Ming-Hsuan
Van Gool, Luc
Wang, Kaiwei
contents Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demonstrating strong capability in handling diverse unknown optical degradations. This work proposes the OmniLens++ framework, which resolves two challenges that hinder the generalization ability of existing pipelines: the difficulty of scaling data and the absence of prior guidance characterizing optical degradation. To improve data scalability, we expand the design specifications to increase the degradation diversity of the lens source, and we sample a more uniform distribution by quantifying the spatial-variation patterns and severity of optical degradation. In terms of model design, to leverage the Point Spread Functions (PSFs), which intuitively describe optical degradation, as guidance in a blind paradigm, we propose the Latent PSF Representation (LPR). The VQVAE framework is introduced to learn latent features of LensLib's PSFs, which is assisted by modeling the optical degradation process to constrain the learning of degradation priors. Experiments on diverse aberrations of real-world lenses and synthetic LensLib show that OmniLens++ exhibits state-of-the-art generalization capacity in blind aberration correction. Beyond performance, the AODLibpro is verified as a scalable foundation for more effective training across diverse aberrations, and LPR can further tap the potential of large-scale LensLib. The source code and datasets will be made publicly available at https://github.com/zju-jiangqi/OmniLens2.
format Preprint
id arxiv_https___arxiv_org_abs_2511_17126
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OmniLens++: Blind Lens Aberration Correction via Large LensLib Pre-Training and Latent PSF Representation
Jiang, Qi
Qian, Xiaolong
Gao, Yao
Sun, Lei
Yang, Kailun
Yi, Zhonghua
Li, Wenyong
Yang, Ming-Hsuan
Van Gool, Luc
Wang, Kaiwei
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Optics
Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demonstrating strong capability in handling diverse unknown optical degradations. This work proposes the OmniLens++ framework, which resolves two challenges that hinder the generalization ability of existing pipelines: the difficulty of scaling data and the absence of prior guidance characterizing optical degradation. To improve data scalability, we expand the design specifications to increase the degradation diversity of the lens source, and we sample a more uniform distribution by quantifying the spatial-variation patterns and severity of optical degradation. In terms of model design, to leverage the Point Spread Functions (PSFs), which intuitively describe optical degradation, as guidance in a blind paradigm, we propose the Latent PSF Representation (LPR). The VQVAE framework is introduced to learn latent features of LensLib's PSFs, which is assisted by modeling the optical degradation process to constrain the learning of degradation priors. Experiments on diverse aberrations of real-world lenses and synthetic LensLib show that OmniLens++ exhibits state-of-the-art generalization capacity in blind aberration correction. Beyond performance, the AODLibpro is verified as a scalable foundation for more effective training across diverse aberrations, and LPR can further tap the potential of large-scale LensLib. The source code and datasets will be made publicly available at https://github.com/zju-jiangqi/OmniLens2.
title OmniLens++: Blind Lens Aberration Correction via Large LensLib Pre-Training and Latent PSF Representation
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Optics
url https://arxiv.org/abs/2511.17126