Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feijoo, Daniel, Garrido-Mellado, Paula, Conde, Marcos V., Rim, Jaesung, Garcia, Alvaro, Cho, Sunghyun, Timofte, Radu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915554779987968
author Feijoo, Daniel
Garrido-Mellado, Paula
Conde, Marcos V.
Rim, Jaesung
Garcia, Alvaro
Cho, Sunghyun
Timofte, Radu
author_facet Feijoo, Daniel
Garrido-Mellado, Paula
Conde, Marcos V.
Rim, Jaesung
Garcia, Alvaro
Cho, Sunghyun
Timofte, Radu
contents This paper reviews the AIM 2025 Efficient Real-World Deblurring using Single Images Challenge, which aims to advance in efficient real-blur restoration. The challenge is based on a new test set based on the well known RSBlur dataset. Pairs of blur and degraded images in this dataset are captured using a double-camera system. Participant were tasked with developing solutions to effectively deblur these type of images while fulfilling strict efficiency constraints: fewer than 5 million model parameters and a computational budget under 200 GMACs. A total of 71 participants registered, with 4 teams finally submitting valid solutions. The top-performing approach achieved a PSNR of 31.1298 dB, showcasing the potential of efficient methods in this domain. This paper provides a comprehensive overview of the challenge, compares the proposed solutions, and serves as a valuable reference for researchers in efficient real-world image deblurring.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12788
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report
Feijoo, Daniel
Garrido-Mellado, Paula
Conde, Marcos V.
Rim, Jaesung
Garcia, Alvaro
Cho, Sunghyun
Timofte, Radu
Computer Vision and Pattern Recognition
This paper reviews the AIM 2025 Efficient Real-World Deblurring using Single Images Challenge, which aims to advance in efficient real-blur restoration. The challenge is based on a new test set based on the well known RSBlur dataset. Pairs of blur and degraded images in this dataset are captured using a double-camera system. Participant were tasked with developing solutions to effectively deblur these type of images while fulfilling strict efficiency constraints: fewer than 5 million model parameters and a computational budget under 200 GMACs. A total of 71 participants registered, with 4 teams finally submitting valid solutions. The top-performing approach achieved a PSNR of 31.1298 dB, showcasing the potential of efficient methods in this domain. This paper provides a comprehensive overview of the challenge, compares the proposed solutions, and serves as a valuable reference for researchers in efficient real-world image deblurring.
title Efficient Real-World Deblurring using Single Images: AIM 2025 Challenge Report
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.12788