NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Dataset and Study

TL;DR

This paper presents a new large-scale video dataset and analyzes state-of-the-art methods from the NTIRE 2021 challenge, demonstrating advancements in compressed video quality enhancement.

Contribution

Introduction of the LDV dataset and comprehensive analysis of challenge methods, advancing the state-of-the-art in compressed video enhancement.

Findings

The NTIRE 2021 challenge improved quality enhancement techniques.

The LDV dataset is publicly available for future research.

Challenge methods outperform previous approaches.

Abstract

This paper introduces a novel dataset for video enhancement and studies the state-of-the-art methods of the NTIRE 2021 challenge on quality enhancement of compressed video. The challenge is the first NTIRE challenge in this direction, with three competitions, hundreds of participants and tens of proposed solutions. Our newly collected Large-scale Diverse Video (LDV) dataset is employed in the challenge. In our study, we analyze the proposed methods of the challenge and several methods in previous works on the proposed LDV dataset. We find that the NTIRE 2021 challenge advances the state-of-the-art of quality enhancement on compressed video. The proposed LDV dataset is publicly available at the homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh