CLIP-RestoreX: Restore Image Structure and Perception in Exposure Correction
Xiang Huang, Qing Zhang, Jian-Fang Hu, Wei-Shi Zheng
Abstract
Exposure correction aims to adjust the exposure of an under- and over-exposed image to enhance its overall visual quality. The core challenge of this task lies in that it requires to faithfully restore both the structure and perception information. In this work, we present a novel exposure correction method, referred to as CLIP-RestoreX, that leverages structural and perceptual priors from CLIP to tackle exposure correction. Specifically, we in CLIP-RestoreX propose to perform exposure correction by aligning CLIP-based structural and perceptual feature of the impaired image with its ground-truth image. To better restore the damaged structural information and perceptual information, we further design a frequency-domain based feature enhancement diffusion model, where we utilize the globality of Fourier transform to help reveal potential the relationship within the features. We conduct extensive experiments on several benchmark datasets. The results demonstrate that the proposed CLIP-RestoreX outperforms state-of-the-art exposure correction methods.
BibTeX
@article{Huang_Zhang_Hu_Zheng_2025, title={CLIP-RestoreX: Restore Image Structure and Perception in Exposure Correction}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/32392}, DOI={10.1609/aaai.v39i4.32392}, abstractNote={Exposure correction aims to adjust the exposure of an under- and over-exposed image to enhance its overall visual quality. The core challenge of this task lies in that it requires to faithfully restore both the structure and perception information. In this work, we present a novel exposure correction method, referred to as CLIP-RestoreX, that leverages structural and perceptual priors from CLIP to tackle exposure correction. Specifically, we in CLIP-RestoreX propose to perform exposure correction by aligning CLIP-based structural and perceptual feature of the impaired image with its ground-truth image. To better restore the damaged structural information and perceptual information, we further design a frequency-domain based feature enhancement diffusion model, where we utilize the globality of Fourier transform to help reveal potential the relationship within the features. We conduct extensive experiments on several benchmark datasets. The results demonstrate that the proposed CLIP-RestoreX outperforms state-of-the-art exposure correction methods.}, number={4}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Huang, Xiang and Zhang, Qing and Hu, Jian-Fang and Zheng, Wei-Shi}, year={2025}, month={Apr.}, pages={3760-3768} }