自动化学报2025，Vol.51Issue(6)：1261-1276,16.DOI:10.16383/j.aas.c240517
梯度引导的JPEG压缩图像超分辨率重建
Gradient-guided Super-resolution Reconstruction for JPEG-compressed Images
摘要
Abstract
In real-world scenarios,images are often affected by multiple degradation factors simultaneously,such as low resolution,compression distortions,and noise.Existing methods typically focus on addressing a single type of degradation,making them less effective when dealing with complex compound degradations.To tackle the com-monly encountered compound degradation issue of low resolution and JPEG compression artifacts in real-world scenarios,we propose a gradient-guided joint JPEG compression artifact removal and super-resolution reconstruc-tion network.The proposed network adopts the super-resolution branch as the leading branch,which asymmetric-ally integrates features from the JPEG compression artifact removal and gradient-guided branches to achieve high-quality image reconstruction.The JPEG compression artifact removal branch focuses on suppressing compression artifacts,thereby alleviating the reconstruction burden on the leading branch.The gradient-guided branch accur-ately estimates image gradients to guide the leading branch in restoring fine details and textures.Experimental res-ults demonstrate that the proposed method improves the reconstruction quality of low-resolution JPEG-compressed images.关键词
JPEG压缩/超分辨率/图像重建/梯度先验Key words
JPEG compression/super-resolution/image reconstruction/gradient prior引用本文复制引用
曹坪,林树冉,张淳杰,郑晓龙,赵耀..梯度引导的JPEG压缩图像超分辨率重建[J].自动化学报,2025,51(6):1261-1276,16.基金项目
国家自然科学基金(62476021,72225011,72434005,62072026),多模态人工智能系统全国重点实验室开放课题基金(MAIS2024106)资助Supported by National Natural Science Foundation of China(62476021,72225011,72434005,62072026)and Open Projects Program of State Key Laboratory of Multimodal Artificial Intelli-gence Systems(MAIS2024106) （62476021,72225011,72434005,62072026）
