Real-World Image Reflection Removal: An Ultra-High-Definition Dataset and an Efficient Baseline

作     者：Chen, Guang-Yong Zheng, Chao-Wei Fan, Guodong Su, Jian-Nan Gan, Min Philip Chen, C. L. 

作者机构：Fuzhou Univ Coll Comp & Data Sci Fuzhou 350116 Peoples R China Minist Educ Fujian Key Lab Network Comp & Intelligent Informat Key Lab Intelligent Metro Univ Fujian Fuzhou 350108 Peoples R China Qingdao Univ Coll Comp Sci & Technol Qingdao 266071 Peoples R China Putian Univ New Engn Ind Coll Putian 351100 Fujian Peoples R China Putian Univ Putian Elect Informat Ind Technol Res Inst Putian 351100 Fujian Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510641 Peoples R China Minist Educ Engn Res Ctr Big Data Intelligence Fuzhou 350108 Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》 (IEEE Trans Circuits Syst Video Technol)

年 卷 期：2025年第35卷第5期

页      面：4397-4408页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：National Natural Science Foundation of China [62173091, 62073082] Natural Science Foundation of Fujian Province [2024J09021, 2023J01268] Special Funds for Promoting High-Quality Development of Marine and Fishery Industries in Fujian Province [FJHYF-ZH-2023-02] Putian Science and Technology Plan Project [2023GJGZ003] 

主　　题：Reflection Image resolution Feature extraction Photography Kernel Image reconstruction Glass Deep learning Circuits and systems Benchmark testing Single-image reflection removal image reconstruction benchmark dataset 

摘      要：Reflection removal is a crucial issue in image reconstruction, especially for high-definition images. Removing undesirable reflections can greatly enhance the performance of various visual systems, such as medical imaging, autonomous driving, and security surveillance. However, the resolution of existing reflection removal datasets is not high and the training data heavily relies on synthetic data, which hampers the performance of reflection removal methods and restricts the development of effective techniques tailored for high-definition images. Therefore, this paper introduces a new dataset, Real-world Reflection Removal in 4K (RR4K). This novel dataset, with its large capacity and high resolution of 6000x 4000 pixels, represents a significant advancement in the field, ensuring a realistic and high quality benchmark. Furthermore, building upon the dataset, we propose an efficient method for single-image reflection removal, optimized for high-definition processing. This method employs the U-Net architecture, enhanced with large kernel distillation and scale-aware features, enabling it to effectively handle complex reflection scenarios while reducing computational demands. Comprehensive testing on the RR4K dataset and existing low-resolution datasets has demonstrated the method s superior efficiency and effectiveness. We believe that our constructed RR4K dataset can better evaluate and design algorithms for removing undesirable reflection from real-world high-definition images. Our dataset and code are available at https://***/jengchauwei/RR4K.