EvenFormer: Dynamic Even Transformer for Real-World Image Restoration

作者：Xin Lu, Yuanfei Bao, Jiarong Yang, A. Hu, Jie Xiao, Kunyu Wang, Dong Li, Senyan Xu, Kean Liu, Xueyang Fu, Zheng-Jun Zha · 年份：2025 · DOI：10.1109/cvprw67362.2025.00105 · 被引用次数：7 · 研究领域：Advanced Image Processing Techniques、Image and Signal Denoising Methods、Medical Image Segmentation Techniques

Ambient Lighting Normalization aims to restore clear image information in complex real-world scenarios. To address the intricate image restoration challenges in realworld high-resolution images, this paper proposes a novel two-stage network Dynamic Even Transformer for RealWorld Image Restoration (EvenFormer). The first-stage network employs a Transformer architecture to model long sequential information. To tackle the unevenness and randomness in image degradation, we utilize a pixel-wise Gaussian shuffling method to aid in global interaction modeling, effectively restoring authentic background information under complex degradation conditions. In the second stage, we introduce the NAFNet network based on a CNN architecture to further refine large-scale images while eliminating blocky interference artifacts caused by the window-based modeling in the Transformer. Experimental results on official datasets validate the superiority of EvenFormer compared to existing approaches.