Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey

作者：Marcos V. Conde, Zhijun Lei, Wen Li, Cosmin Stejerean, Ioannis Katsavounidis, R. Timofte, Kihwan Yoon, G. Gankhuyag, Jiangtao Lv, Long Sun, Jinshan Pan, Jiangxin Dong, Jinhui Tang, Zhi-Ying Li, Hao Wei, Chenyang Ge, Dongyang Zhang, Tianle Liu, H. Chen, Yi Jin, Meng-Ying Zhou, Yi-Fang Yan, Si-feng Gao, Biao Wu, Shaoli Liu, Cheng-yong Zheng, Diankai Zhang, Ning Wang, Xintao Qiu, Yuan Zhou, Kongxian Wu, Xi Dai, Hui Tang, Weiying Deng, Qingquan Gao, Tong Tong, Jae-hyeon Lee, Ui-Jin Choi, Min Yan, Xin Liu, Qian Wang, Xiao-Han Ye, Zhanwei Du, Tian‐Min Zhang, Long Peng, Jiaming Guo, Xin Di, Bohao Liao, Zhibo Du, P. Xia, Renjing Pei, Yang Wang, Yang Cao, Zhengjun Zha, Bingnan Han, Hongyuan Yu, Zhuoyuan Wu, Cheng Wan, Yuqing Liu, Hao-Nan Yu, Jizhe Li, Zhijuan Huang, Yuan Huang, Yajun Zou, Xianyu Guan, Qilong Jia, Heng-Ming Zhang, Xuanwu Yin, Kunlong Zuo, Hyeon-Cheol Moon, T. Jeong, Yoonmo Yang, Jae-Gon Kim, Jinwoo Jeong, Sun-jeong Kim · 发表于：2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 年份：2024 · DOI：10.1109/CVPRW63382.2024.00592 · 被引用次数：26 · 研究领域：Computer Science、Engineering

This paper introduces a novel benchmark for efficient image upscaling as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to up scale compressed images from 540p to native 4K resolution (4x factor) in real-time on commercial GPUs. For this, we use a diverse test set containing diverse 4K images ranging from digital art to gaming and photography. The images are compressed using the modern AVIF codec, instead of JPEG. All the proposed methods improve PSNR fidelity over Lanczos interpolation, and process images under 30ms. Out of the 160 participants, 25 teams submitted their code. This survey considers only the most novel solutions models, making it the most comprehensive benchmark on real-time SR of compressed images using modern codecs.