Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results

Maksim Smirnov, Aleksandr Gushchin, Anastasia Antsiferova, Dmitry Vatolin, Radu Timofte, Ziheng Jia, Zicheng Zhang, Wei Sun, Jiaying Qian, Yuqin Cao, Yinan Sun, Yuxin Zhu, Xiongkuo Min, Guangtao Zhai, Kanjar De, Qing Luo, Ao-Xiang Zhang, Peng Zhang, Haibo Lei, Linyan Jiang, Yaqing Li, Wenhui Meng, Zhenzhong Chen, Zhengxue Cheng, Jiahao Xiao, Jun Xu, Chenlong He, Qi Zheng, Ruoxi Zhu, Min Li, Yibo Fan, Zhengzhong Tu

TL;DR

The results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation workshop at ECCV 2024, are presented, providing a comprehensive benchmark for future research.

Abstract

Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H.264, HEVC/H.265, AV1, and VVC/H.266) and containing a comprehensive collection of compression artifacts. To measure the methods performance, we employed traditional correlation coefficients between their predictions and subjective scores, which were collected via large-scale crowdsourced pairwise human comparisons. For training purposes, participants were provided with the Compressed Video Quality Assessment Dataset (CVQAD), a previously developed dataset of 1022 videos. Up to 30 participating teams registered for the challenge, while we report the results of 6 teams, which submitted valid final solutions and code for reproducing the results. Moreover, we calculated and present the performance of state-of-the-art VQA methods on the developed dataset, providing a comprehensive benchmark for future research. The dataset, results, and online leaderboard are publicly available at https://challenges.videoprocessing.ai/challenges/compressedvideo-quality-assessment.html.

AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results

TL;DR

The results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation workshop at ECCV 2024, are presented, providing a comprehensive benchmark for future research.

Abstract

Video quality assessment (VQA) is a crucial task in the development of video compression standards, as it directly impacts the viewer experience. This paper presents the results of the Compressed Video Quality Assessment challenge, held in conjunction with the Advances in Image Manipulation (AIM) workshop at ECCV 2024. The challenge aimed to evaluate the performance of VQA methods on a diverse dataset of 459 videos, encoded with 14 codecs of various compression standards (AVC/H.264, HEVC/H.265, AV1, and VVC/H.266) and containing a comprehensive collection of compression artifacts. To measure the methods performance, we employed traditional correlation coefficients between their predictions and subjective scores, which were collected via large-scale crowdsourced pairwise human comparisons. For training purposes, participants were provided with the Compressed Video Quality Assessment Dataset (CVQAD), a previously developed dataset of 1022 videos. Up to 30 participating teams registered for the challenge, while we report the results of 6 teams, which submitted valid final solutions and code for reproducing the results. Moreover, we calculated and present the performance of state-of-the-art VQA methods on the developed dataset, providing a comprehensive benchmark for future research. The dataset, results, and online leaderboard are publicly available at https://challenges.videoprocessing.ai/challenges/compressedvideo-quality-assessment.html.
Paper Structure (28 sections, 7 figures, 3 tables)

This paper contains 28 sections, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Challenge
  3. Challenge datasets
  4. Evaluation protocol
  5. Challenge phases
  6. Challenge results
  7. Challenge Teams and Solutions
  8. TVQA-C
  9. TVQA
  10. SJTU-MultimediaLab
  11. Compression-RQ-VQA
  12. FudanVIP
  13. COVER
  14. Test IQA
  15. MMF Multimethod Fusion
  16. ...and 13 more sections

Figures (7)

  • Figure 1: Samples from the videos in the CVQAC validation and test sets.
  • Figure 2: Architecture of TVQA, proposed by TVQA-C team.
  • Figure 3: The overall structure of the Compression-RQ-VQA, proposed by SJTU-MultimediaLab, where KFI means key frames input (only extract one frame each second for input) and DFI means dense frames input (all the frames in the video are input).
  • Figure 4: The architecture of COmprehensive Video quality EvaluatoR (COVER), proposed by team FudanVIP. COVER processes a video clip in three parallel branches: 1) a semantic branch that extracts high-level object-semantics-related information using a pre-trained CLIP image Encoder; 2) an aesthetic branch that leverages a ConvNet run on subsampled image thumbnails to analyze their looking; 3) a technical branch utilizing Swin Transformer to execute on fragments. The simplified cross-gating block (SCGB) is designed to fuse multi-branch features together, yielding the final quality score.
  • Figure 5: System Block Diagram for MMF Multimethod Fusion, proposed by Test IQA.
  • ...and 2 more figures