학술논문

Efficient Deep Models for Real-Time 4K Image Super-Resolution. NTIRE 2023 Benchmark and Report
Document Type
Conference
Source
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) CVPRW Computer Vision and Pattern Recognition Workshops (CVPRW), 2023 IEEE/CVF Conference on. :1495-1521 Jun, 2023
Subject
Computing and Processing
Engineering Profession
Training
Photography
Interpolation
Runtime
Superresolution
Digital art
Benchmark testing
Language
ISSN
2160-7516
Abstract
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.