文献类型：期刊文献

英文题名：Joint Luminance-Chrominance Learning for Image Debanding

作者：Chen, Zijian[1];Sun, Wei[1];Jia, Jun[1];Huang, Ru[2];Lu, Fangfang[3];Chen, Ying[4];Min, Xiongkuo[1];Zhai, Guangtao[1];Zhang, Wenjun[1]

机构：[1]Shanghai Jiao Tong Univ, Inst Image Commun & Informat Proc, Shanghai 200240, Peoples R China;[2]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[3]Shanghai Univ Elect Power, Coll Comp Sci & Technol, Shanghai 200290, Peoples R China;[4]Alibaba Grp, Hangzhou 311121, Peoples R China

年份：2025

卷号：35

期号：8

起止页码：7747

外文期刊名：IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY

收录：;EI(收录号：20250917953247);WOS:【SCI-EXPANDED(收录号:WOS:001549816500023)】；

基金：This work was supported in part by the National Key Research and Development Program of China under Grant 2021YFE0206700; in part by the China Postdoctoral Science Foundation (CPSF) under Grant 2023TQ0212 and Grant 2023M742298; in part by the Postdoctoral Fellowship Program of CPSF under Grant GZC20231618; in part by Shanghai Pujiang Program under Grant 22PJ1407400; and in part by the National Natural Science Foundation of China under Grant 62271312, Grant 62301316, Grant 62101325, and Grant 62101326.

语种：英文

外文关键词：Image color analysis; Image restoration; Image coding; Visualization; Training; Filters; Distortion; Quantization (signal); Quality of experience; Feature extraction; Image debanding; false contour removal; luminance; chrominance; image quality enhancement

摘要：Banding is a visually annoying artifact that frequently occurs along the chain of video acquisition, production, distribution, and display, showing a significant need for improvement in many fields. Thus far, efforts on banding removal are mainly knowledge-driven or merely learning on RGB space, which is either limited by domain knowledge or lacks the consideration for banding in chrominance channels. In this work, we propose a unified deep neural network that explicitly disentangles the luminance and chrominance channels, and simultaneously recovers intensity gradients and color discontinuity from detection-free measurement in an end-to-end manner. Our debanding model is comprised of a luminance restoration network (LR-Net) and a chrominance restoration network (CR-Net). Each of them follows an encoder-decoder architecture, where a cascade of residual blocks is employed to exploit hierarchical non-local features in spatial dimensions for more powerful feature representation. Moreover, we investigate the characteristics of banding artifacts and apply specific loss functions to guide the debanding in different channels, thus boosting the restoration performance. Both qualitative and quantitative experiments show that our model significantly surpasses the existing method in terms of all 7 metrics. Ultimately, our network trained on simulated data exhibits good adaptiveness under various compression scenarios, which further demonstrates the effectiveness of the proposed model.