Efficient Deep Models for Real-Time 4K Image Super-Resolution. NTIRE 2023 Benchmark and Report.

CVPR Workshops(2023)

引用 19|浏览43
暂无评分
摘要
This paper introduces a novel benchmark for efficient up-scaling as part of the NTIRE 2023 Real-Time Image Super-Resolution (RTSR) Challenge, which aimed to upscale images from 720p and 1080p resolution to native 4K (×2 and ×3 factors) in real-time on commercial GPUs. For this, we use a new test set containing diverse 4K images ranging from digital art to gaming and photography. We assessed the methods devised for 4K SR by measuring their runtime, parameters, and FLOPs, while ensuring a minimum PSNR fidelity over Bicubic interpolation. Out of the 170 participants, 25 teams contributed to this report, making it the most comprehensive benchmark to date and showcasing the latest advancements in real-time SR.
更多
查看译文
关键词
4K SR,Bicubic interpolation,digital art,diverse 4K images,efficient deep models,FLOP,gaming,GPU,NTIRE 2023 benchmark,NTIRE 2023 Real-Time Image Super-Resolution,photography,PSNR fidelity,real-time 4K image super-resolution,real-time SR,upscale images
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要