Method Overview
Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors. This degradation affects image details, color accuracy, and presents challenges in computational photography. Existing vignetting removal algorithms predominantly rely on ideal physics assumptions and hand-crafted parameters, resulting in ineffective removal of irregular vignetting and suboptimal results. Moreover, the substantial lack of real-world vignetting datasets hinders the objective and comprehensive evaluation of vignetting removal. To address these challenges, we present Vigset, a pioneering dataset for vignette removal. Vigset includes 983 pairs of both vignetting and vignetting-free high-resolution (5340×3697) real-world images under various conditions. In addition, We introduce DeVigNet, a novel frequency-aware Transformer architecture designed for vignetting removal. Through the Laplacian Pyramid decomposition, we propose the Dual Aggregated Fusion Transformer to handle global features and remove vignetting in the low-frequency domain. Additionally, we introduce the Adaptive Channel Expansion Module to enhance details in the high-frequency domain. The experiments demonstrate that the proposed model outperforms existing state-of-the-art methods. The code, models, and dataset are available at here.
@article{Luo_Chen_Chen_Li_Wang_Pun_2024,
title={Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer with Adaptive Channel Expansion},
volume={38},
DOI={10.1609/aaai.v38i5.28193},
number={5},
journal={Proceedings of the AAAI Conference on Artificial Intelligence},
author={Luo, Shenghong and Chen, Xuhang and Chen, Weiwen and Li, Zinuo and Wang, Shuqiang and Pun, Chi-Man},
year={2024},
month={Mar.},
pages={4000-4008}
}
This work was supported in part by the Science and Technology Development Fund, Macau SAR, under Grant 0087/2020/A2 and Grant 0141/2023/RIA2, in part by the National Natural Science Foundations of China under Grant 62172403, in part by the Distinguished Young Scholars Fund of Guangdong under Grant 2021B1515020019, in part by the Excellent Young Scholars of Shenzhen under Grant RCYX20200714114641211.