ICME 2025 Grand Challenge on Video Super-Resolution for Video Conferencing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Naderi, Babak, Cutler, Ross, Cho, Juhee, Khongbantabam, Nabakumar, Ivkovic, Dejan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915367741292544
author Naderi, Babak
Cutler, Ross
Cho, Juhee
Khongbantabam, Nabakumar
Ivkovic, Dejan
author_facet Naderi, Babak
Cutler, Ross
Cho, Juhee
Khongbantabam, Nabakumar
Ivkovic, Dejan
contents Super-Resolution (SR) is a critical task in computer vision, focusing on reconstructing high-resolution (HR) images from low-resolution (LR) inputs. The field has seen significant progress through various challenges, particularly in single-image SR. Video Super-Resolution (VSR) extends this to the temporal domain, aiming to enhance video quality using methods like local, uni-, bi-directional propagation, or traditional upscaling followed by restoration. This challenge addresses VSR for conferencing, where LR videos are encoded with H.265 at fixed QPs. The goal is to upscale videos by a specific factor, providing HR outputs with enhanced perceptual quality under a low-delay scenario using causal models. The challenge included three tracks: general-purpose videos, talking head videos, and screen content videos, with separate datasets provided by the organizers for training, validation, and testing. We open-sourced a new screen content dataset for the SR task in this challenge. Submissions were evaluated through subjective tests using a crowdsourced implementation of the ITU-T Rec P.910.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12269
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ICME 2025 Grand Challenge on Video Super-Resolution for Video Conferencing
Naderi, Babak
Cutler, Ross
Cho, Juhee
Khongbantabam, Nabakumar
Ivkovic, Dejan
Image and Video Processing
Computer Vision and Pattern Recognition
Multimedia
Super-Resolution (SR) is a critical task in computer vision, focusing on reconstructing high-resolution (HR) images from low-resolution (LR) inputs. The field has seen significant progress through various challenges, particularly in single-image SR. Video Super-Resolution (VSR) extends this to the temporal domain, aiming to enhance video quality using methods like local, uni-, bi-directional propagation, or traditional upscaling followed by restoration. This challenge addresses VSR for conferencing, where LR videos are encoded with H.265 at fixed QPs. The goal is to upscale videos by a specific factor, providing HR outputs with enhanced perceptual quality under a low-delay scenario using causal models. The challenge included three tracks: general-purpose videos, talking head videos, and screen content videos, with separate datasets provided by the organizers for training, validation, and testing. We open-sourced a new screen content dataset for the SR task in this challenge. Submissions were evaluated through subjective tests using a crowdsourced implementation of the ITU-T Rec P.910.
title ICME 2025 Grand Challenge on Video Super-Resolution for Video Conferencing
topic Image and Video Processing
Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2506.12269