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

TL;DR

This paper presents a benchmark and survey of real-time 4K super-resolution methods for compressed AVIF images, highlighting novel, efficient solutions that outperform traditional interpolation in fidelity and speed on GPUs.

Contribution

It introduces a new benchmark for real-time 4K super-resolution of AVIF images and surveys top solutions emphasizing memory efficiency and rapid processing.

Findings

All methods outperform Lanczos interpolation in PSNR.

Solutions process images under 10ms on GPUs.

25 teams submitted models demonstrating diverse approaches.

Abstract

This paper introduces a novel benchmark as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to upscale compressed images from 540p to 4K resolution (4x factor) in real-time on commercial GPUs. For this, we use a diverse test set containing a variety of 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 10ms. Out of the 160 participants, 25 teams submitted their code and models. The solutions present novel designs tailored for memory-efficiency and runtime on edge devices. This survey describes the best solutions for real-time SR of compressed high-resolution images.