This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track 2 targets the super-resolution of compressed video. In Track 1, we use the popular dataset DIV2K as the training, validation and test sets. In Track 2, we propose the LDV 3.0 dataset, which contains 365 videos, including the LDV 2.0 dataset (335 videos) and 30 additional videos. In this challenge, there are 12 teams and 2 teams that submitted the final results to Track 1 and Track 2, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution on compressed image and video. The proposed LDV 3.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge is at https://github.com/RenYang-home/AIM22_CompressSR.

Yang, R., Timofte, R., Li, X., Zhang, Q., Zhang, L., Liu, F., et al. (2023). AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results. In Computer Vision – ECCV 2022 Workshops Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III (pp.174-202). Springer Science and Business Media Deutschland GmbH [10.1007/978-3-031-25066-8_8].

AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results

Rota C.;Buzzelli M.;Bianco S.;Schettini R.;
2023

Abstract

This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. This challenge includes two tracks. Track 1 aims at the super-resolution of compressed image, and Track 2 targets the super-resolution of compressed video. In Track 1, we use the popular dataset DIV2K as the training, validation and test sets. In Track 2, we propose the LDV 3.0 dataset, which contains 365 videos, including the LDV 2.0 dataset (335 videos) and 30 additional videos. In this challenge, there are 12 teams and 2 teams that submitted the final results to Track 1 and Track 2, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution on compressed image and video. The proposed LDV 3.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge is at https://github.com/RenYang-home/AIM22_CompressSR.
slide + paper
Image compression; Super-resolution; Video compression;
English
17th European Conference on Computer Vision, ECCV 2022 - 23 October 2022through 27 October 2022
2022
Karlinsky, L; Michaeli, T; Nishino, K
Computer Vision – ECCV 2022 Workshops Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III
9783031250651
18-feb-2023
2023
13803 LNCS
174
202
open
Yang, R., Timofte, R., Li, X., Zhang, Q., Zhang, L., Liu, F., et al. (2023). AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results. In Computer Vision – ECCV 2022 Workshops Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III (pp.174-202). Springer Science and Business Media Deutschland GmbH [10.1007/978-3-031-25066-8_8].
File in questo prodotto:
File Dimensione Formato  
Yang-2023-Lect Notes Computer Sci-preprint .pdf

accesso aperto

Descrizione: Conference Paper
Tipologia di allegato: Submitted Version (Pre-print)
Licenza: Creative Commons
Dimensione 8.07 MB
Formato Adobe PDF
8.07 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/415436
Citazioni
  • Scopus 10
  • ???jsp.display-item.citation.isi??? ND
Social impact