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

TL;DR

OmniLens++ introduces a scalable, pre-trained deep learning framework that uses latent PSF representations to effectively correct diverse lens aberrations, demonstrating state-of-the-art generalization in blind optical degradation correction.

Contribution

The paper presents OmniLens++, a novel framework that leverages large-scale lens library pre-training and latent PSF modeling to improve generalization in blind lens aberration correction.

Findings

OmniLens++ achieves state-of-the-art correction performance on real-world and synthetic lenses.

The framework demonstrates strong generalization across diverse optical aberrations.

Latent PSF representations enhance the model's ability to utilize optical degradation priors.

Abstract

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.