# OmniLens: Towards Universal Lens Aberration Correction via LensLib-to-Specific Domain Adaptation

arXiv: https://arxiv.org/abs/2409.05809 · HTML: https://mlsanity.com/paper/2409.05809/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 65 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [Domain Adaptation for Image Dehazing](https://mlsanity.com/paper/2005.04668/) (2020)
- [Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors](https://mlsanity.com/paper/2202.13142/) (2022)
- [Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training](https://mlsanity.com/paper/2004.01178/) (2020)
- [Domain Adaptation for Underwater Image Enhancement](https://mlsanity.com/paper/2108.09650/) (2021)
- [Curriculum Learning for ab initio Deep Learned Refractive Optics](https://mlsanity.com/paper/2302.01089/) (2023)
- [Fast Two-step Blind Optical Aberration Correction](https://mlsanity.com/paper/2208.00950/) (2022)
- [Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution](https://mlsanity.com/paper/2104.03078/) (2021)
- [Optical Aberration Correction in Postprocessing using Imaging Simulation](https://mlsanity.com/paper/2305.05867/) (2023)
- [Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers](https://mlsanity.com/paper/2306.12992/) (2023)
- [Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution](https://mlsanity.com/paper/2205.03524/) (2022)
- [Computational Optics for Mobile Terminals in Mass Production](https://mlsanity.com/paper/2305.05886/) (2023)
- [NTIRE 2024 Restore Any Image Model (RAIM) in the Wild Challenge](https://mlsanity.com/paper/2405.09923/) (2024)
- [Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision](https://mlsanity.com/paper/2109.08880/) (2021)
- [Computational Imaging for Machine Perception: Transferring Semantic Segmentation beyond Aberrations](https://mlsanity.com/paper/2211.11257/) (2022)
- [Exploring Quasi-Global Solutions to Compound Lens Based Computational Imaging Systems](https://mlsanity.com/paper/2404.19201/) (2024)
- [Mobile Image Restoration via Prior Quantization](https://mlsanity.com/paper/2305.05899/) (2023)

## Built on by (most cited first, 4 of 4)

- [Learning Latent Transmission and Glare Maps for Lens Veiling Glare Removal](https://mlsanity.com/paper/2511.17353/) (2025)
- [Towards Blind Lens Aberration Correction via Large LensLib Pre-training and Discrete Degradation Priors](https://mlsanity.com/paper/2511.17126/) (2025)
- [Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis](https://mlsanity.com/paper/2603.12083/) (2026)
- [LensBridge: Frequency-Guided Compound Degradation Adaptation for Lens Aberration Correction and Veiling Glare Removal](https://mlsanity.com/paper/2610.00318/) (2026)

## Abstract (arXiv)

Emerging universal Computational Aberration Correction (CAC) paradigms provide an inspiring solution to light-weight and high-quality imaging with a universal model trained on a lens library (LensLib) to address arbitrary lens optical aberrations blindly. However, the limited coverage of existing LensLibs leads to poor generalization of the trained models to unseen lenses, whose fine-tuning pipeline is also confined to the lens-descriptions-known case. In this work, we introduce OmniLens, a flexible solution to universal CAC via (i) establishing a convincing LensLib with comprehensive coverage for pre-training a robust base model, and (ii) adapting the model to any specific lens designs with unknown lens descriptions via fast LensLib-to-specific domain adaptation. To achieve these, an Evolution-based Automatic Optical Design (EAOD) pipeline is proposed to generate a rich variety of lens samples with realistic aberration behaviors. Then, we design an unsupervised regularization term for efficient domain adaptation on a few easily accessible real-captured images based on the statistical observation of dark channel priors in degradation induced by lens aberrations. Extensive experiments demonstrate that the LensLib generated by EAOD effectively develops a universal CAC model with strong generalization capabilities, which can also improve the non-blind lens-specific methods by 0.35~1.81dB in PSNR. Additionally, the proposed domain adaptation method significantly improves the base model, especially in severe aberration cases (at most 2.59dB in PSNR). The code and data will be available at https://github.com/zju-jiangqi/OmniLens.