eess.IVSep 29, 2026

LensBridge: Frequency-Guided Compound Degradation Adaptation for Lens Aberration Correction and Veiling Glare Removal

Authors: Xiaolong Qian, Zhonghua Yi, Qi Jiang, Kailun Yang, Shuhang Xie, Shaohua Gao, Kaiwei Wang

Organizations: Zhejiang University · Hunan University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Simplified optical systems often exhibit residual lens aberrations and Veiling Glare (VG), resulting in spatially varying blur and contrast reduction. Large-scale Lens Libraries (LensLib) enable reusable aberration correction models by covering diverse Point Spread Functions (PSFs), but their aberration-only training distribution does not include target-specific veiling glare. Extending such foundations to compound degradation is challenging because realistic target-system compound pairs are difficult to obtain. To address this challenge, we propose LensBridge, a two-stage framework that first establishes a reusable aberration correction foundation and then adapts it to compound optical degradation using only a few unpaired target observations. In Stage I, we build a PSF-aware one-step diffusion foundation by constructing discrete degradation priors from LensLib PSFs and learning to retrieve them directly from aberrated images, enabling PSF-aware correction without requiring explicit PSF at inference. In Stage II, we adapt this foundation to compound degradation through frequency-domain guidance. At the data level, Frequency-guided Degradation Completion (FDC) transfers target low-frequency characteristics to LensLib aberrated images while preserving aberration structures to synthesize compound training pairs; at the model level, Frequency-guided Pseudo Decomposition (FPD) forms aberration- and VG-dominant pseudo observations to condition separate adaptation branches. Extensive experiments across multiple optical systems demonstrate that LensBridge effectively extends reusable aberration correction foundations to joint aberration correction and veiling glare removal without target-system paired supervision. All code will be available at https://github.com/XiaolongQian/LensBridge.

Figures & tables

Figure 1: Motivation for LensBridge . (a) Comparison of optical adaptation paradigms in terms of source pretraining and target degradation. LensBridge adapts a reusable aberration correction foundation to target compound degradation using only unpaired target images. (b) In the illustrated example, aberration induces broadband amplitude changes, whereas the additional veiling glare produces predominantly low-frequency amplitude changes and a smaller phase-swap reconstruction error in the illustrated example, motivating the frequency-guided designs of FDC and FPD.
Figure 2: Overview of LensBridge . LensBridge consists of two stages: (a) a reusable PSF-aware aberration correction foundation, where discrete degradation priors are constructed from LensLib PSFs and retrieved directly from aberrated observations; and (b) target-system compound degradation adaptation, where aberration-dominant and VG-dominant pseudo observations separately condition the two adaptation branches. The shared one-step diffusion backbone and the frequency-guided pseudo decomposition mechanism are detailed in (c) and (d), respectively.
Figure 3: Visual results on Screen domain. Zoom in for the best view.
Figure 4: Visual results on Real domain. Zoom in for the best view.
Figure 5: Results on additional optical systems. LensBridge effectively adapts to the CAYE lens and nano-optics system using only a few unpaired target observations.
Figure 6
Figure 7
Figure 8: Analysis of target spectral statistics.
Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Optical SystemDomain# Target ObservationsPurpose
SLScreen50Main benchmark
SLReal50Main benchmark
MRLScreen50Main benchmark
MRLReal50Main benchmark
CAYEReal26Additional optical system
NanoReal3Additional optical system
Appendix
Table 5: Number of unpaired target observations used for few-shot Stage-II adaptation across different optical systems.
Figure 9: t-SNE visualization of blind prior retrieval on representative held-out LensLib lenses. Crosses denote PSF-derived priors, circles denote image-retrieved priors from aberrated observations, and gray lines connect matched GT–prediction pairs.
Figure 10: Additional analysis of the target spectral statistic. (a) Single-image amplitude transfer introduces content-dependent structures into the recomposed images. (b) The estimated target spectral statistic becomes progressively more stable as the number of target observations increases; the right plot reports the distance to the 50-shot statistic.
Spatial ModulationPSNR ↑\uparrowLPIPS ↓\downarrowMUSIQ ↑\uparrowQ-Align ↑\uparrow
×\times20.5050.26863.5564.447
✓\checkmark20.4620.26665.3034.473
Appendix
Table 6: Effect of spatial modulation during FDC on Screen-SL .
Target ImagesPSNR ↑\uparrowLPIPS ↓\downarrowMUSIQ ↑\uparrowQ-Align ↑\uparrow
015.0750.33253.6513.725
519.5510.27764.2834.384
1519.6540.27164.5794.420
2520.0340.27065.1134.436
5020.4620.26665.3034.473
Appendix
Table 9: Few-shot adaptation with unpaired target observations on the Screen SL domain.
Dclr\mathcal{D}_{\mathrm{clr}}CLIP-IQA ↑\uparrowNIQE ↓\downarrowMANIQA ↑\uparrowMUSIQ ↑\uparrowQ-Align ↑\uparrow
Flickr2K0.5494.0030.37260.8844.380
DIV2K0.5724.1500.36760.3204.354
Appendix
Table 10: Sensitivity to the clear reference dataset on the Real SL domain.
Figure 11: Additional visual comparisons on the Screen domain under the unpaired-target setting. Results are shown for both the SL and MRL optical systems. Zoom in for the best view.
Figure 12: Additional visual comparisons on the Real domain under the unpaired-target setting. Results are shown for both the SL and MRL optical systems. Zoom in for the best view.
Figure 13: Additional visual results on the CAYE lens and nano-optics system. Stage I denotes the reusable aberration correction foundation before target adaptation, while LensBridge denotes the adapted model using unpaired target observations. Zoom in for the best view.
Figure 14: Additional visual comparisons on the Screen domain under the target aberration-paired setting. Results are shown for both the SL and MRL systems. Zoom in for the best view.
Figure 15: Additional visual comparisons on the Real domain under the target aberration-paired setting. Results are shown for both the SL and MRL systems. Zoom in for the best view.
Figure 16: Visual results on real UDC images from Feng et al. (2021) . LensBridge provides moderate restoration of contrast and visibility under UDC degradation. Zoom in for the best view.
Figure 17: Failure cases. Fine high-frequency text in SL remains challenging to reconstruct faithfully, while severe overexposure in MRL causes substantial information loss.
More in this topic

Image Restoration

Image restoration uses computational methods to recover useful visual content from noisy, blurred, low-resolution, or otherwise degraded images.

See all 372 papers

Explore similar work

CardsList
Jul 7, 2026

Realistic Compound-Lens Defocus Blur Synthesis

Defocus blur degrades fine image structures and limits visual perception, which can adversely affect downstream vision tasks. Although recent deep learning deblurring methods have achieved strong performance, their effectiveness depends on training data and often degrades across cameras and lenses due to limited optical diversity and realism in existing datasets. In this paper, we propose a pipeline for synthesizing realistic defocus deblurring datasets for diverse compound lenses. It integrates efficient wave-optics PSF computation via Debye CZT propagation, depth-aware defocus rendering with occlusion handling, and blur synthesis in the radiometrically linear space with camera ISP simulation. This unified pipeline enables the scalable generation of photorealistic defocus datasets with diverse lens characteristics. Using our pipeline, we generate CLDefocus, a large-scale synthetic dataset containing lens-diverse defocus image pairs. We further analyze the limitations of real-captured defocus datasets and show that such imperfections can bias full-reference evaluation. Extensive experiments demonstrate that models trained on CLDefocus achieve improved cross-device generalization compared to models trained on existing real and synthetic datasets.

Yunkyu Lee, Woohyeok Kim, Sunghyun Cho

POSTECH, Pohang, Korea

Image DeblurringSynthetic Data GenerationComputational Imaging
AskPDF
May 8, 2026

Breaking Spatial Uniformity: Prior-Guided Mamba with Radial Serialization for Lens Flare Removal

Lens flares, caused by complex optical aberrations, severely degrade image quality especially in nighttime photography. Although recent restoration methods have made remarkable progress, most still rely on spatially uniform processing. They are failing to handle the region-dependent restoration demands of flare scenes, where saturated light sources should be preserved, flare artifacts removed, and background details recovered. To address this challenge, we propose DeflareMambav2, a prior-guided Mamba framework for lens flare removal. Specifically, we introduce a Flare Prior Network (FPN) to estimate flare priors and guide adaptive restoration. Besides, a novel radial serialization strategy breaks spatially homogeneous processing by performing flare-aware targeted sampling, and better supports long-range modeling in State Space Models (SSMs). Based on these priors, the backbone adopts a dual-level adaptive scheme. It explicitly preserves light-source regions to avoid over-processing, and applies curriculum-based restoration to the remaining contaminated areas while calibrating restoration intensity at the pixel level. Extensive experiments demonstrate that DeflareMambav2 achieves state-of-the-art performance with reduced parameter burden. Code is available at https://github.com/BNU-ERC-ITEA/DeflareMambav2.

Zijia Fu, Yuanfei Huang, Lizhi Wang +1

School of Artificial Intelligence, Beijing Normal University, Beijing, China · School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China

MambaImage Restoration
AskPDF
Mar 12, 2026

Towards Universal Computational Aberration Correction in Photographic Cameras: A Comprehensive Benchmark Analysis

Prevalent Computational Aberration Correction (CAC) methods are typically tailored to specific optical systems, leading to poor generalization and labor-intensive re-training for new lenses. Developing CAC paradigms capable of generalizing across diverse photographic lenses offers a promising solution to these challenges. However, efforts to achieve such cross-lens universality within consumer photography are still in their early stages due to the lack of a comprehensive benchmark that encompasses a sufficiently wide range of optical aberrations. Furthermore, it remains unclear which specific factors influence existing CAC methods and how these factors affect their performance. In this paper, we present comprehensive experiments and evaluations involving 24 image restoration and CAC algorithms, utilizing our newly proposed UniCAC, a large-scale benchmark for photographic cameras constructed via automatic optical design. The Optical Degradation Evaluator (ODE) is introduced as a novel framework to objectively assess the difficulty of CAC tasks, offering credible quantification of optical aberrations and enabling reliable evaluation. Drawing on our comparative analysis, we identify three key factors -- prior utilization, network architecture, and training strategy -- that most significantly influence CAC performance, and further investigate their respective effects. We believe that our benchmark, dataset, and observations contribute foundational insights to related areas and lay the groundwork for future investigations. Benchmarks, codes, and Zemax files will be available at https://github.com/XiaolongQian/UniCAC.

Xiaolong Qian, Qi Jiang, Yao Gao +5

Zhejiang University · INSAIT, Sofia University “St. Kliment Ohridski” · Hunan University

Computational ImagingImage Restoration
AskPDF