ML Anthology

AIM 2024 Challenge on UHD Blind Photo Quality Assessment

Vlad Hosu, Marcos V. Conde, Lorenzo Agnolucci, Nabajeet Barman, Saman Zadtootaghaj, Radu Timofte, Wei Sun, Weixia Zhang, Yuqin Cao, Linhan Cao, Jun Jia, Zijian Chen, Zicheng Zhang, Xiongkuo Min, Guangtao Zhai, Songbai Tan, Lixin Zhang, Guanghui Yue, Daekyu Kwon, Dongyoung Kim, Seon Joo Kim, Yunchen Zhang, Xiangkai Xu, Hong Gao, Yiming Bao, Ji Shi, Xiugang Dong, Xiangsheng Zhou, Yaofeng Tu, Zewen Chen, Shunhan Xu, Haochen Guo, Yun Zeng, Shuai Liu, Jian Guo, Juan Wang, Bing Li, Dehua Liu, Hesong Liu, Grigory Malivenko, Asile Gerek, Xingyuan Ma, Cheng Li, Joonhee Lee, Junseo Bang, Se Young Chun
ECCVW 2024 pp. 261-286
doi:10.1007/978-3-031-91856-8_16 /eccvw/2024/hosu2024eccvw-aim/

Abstract

We introduce the AIM 2024 UHD-IQA Challenge, a competition to advance the No-Reference Image Quality Assessment (NR-IQA) task for modern, high-resolution photos. The challenge is based on the recently released UHD-IQA Benchmark Database, which comprises 6,073 UHD-1 (4K) images annotated with perceptual quality ratings from expert raters. Unlike previous NR-IQA datasets, UHD-IQA focuses on highly aesthetic photos of superior technical quality, reflecting the ever-increasing standards of digital photography. This challenge aims to develop efficient and effective NR-IQA models. Participants are tasked with creating novel architectures and training strategies to achieve high predictive performance on UHD-1 images within a computational budget of 50G MACs. This enables model deployment on edge devices and scalable processing of extensive image collections. Winners are determined based on a combination of performance metrics, including correlation measures (SRCC, PLCC, KRCC), absolute error metrics (MAE, RMSE), and computational efficiency (G MACs). To excel in this challenge, participants leverage techniques like knowledge distillation, low-precision inference, and multi-scale training. By pushing the boundaries of NR-IQA for high-resolution photos, the UHD-IQA Challenge aims to stimulate the development of practical models that can keep pace with the rapidly evolving landscape of digital photography. The innovative solutions emerging from this competition will have implications for various applications, from photo curation and enhancement to image compression.

PDF ECCVW Semantic Scholar

Cite

Text

Hosu et al. "AIM 2024 Challenge on UHD Blind Photo Quality Assessment." European Conference on Computer Vision Workshops, 2024. doi:10.1007/978-3-031-91856-8_16

Markdown

[Hosu et al. "AIM 2024 Challenge on UHD Blind Photo Quality Assessment." European Conference on Computer Vision Workshops, 2024.](https://mlanthology.org/eccvw/2024/hosu2024eccvw-aim/) doi:10.1007/978-3-031-91856-8_16

BibTeX

@inproceedings{hosu2024eccvw-aim,
  title     = {{AIM 2024 Challenge on UHD Blind Photo Quality Assessment}},
  author    = {Hosu, Vlad and Conde, Marcos V. and Agnolucci, Lorenzo and Barman, Nabajeet and Zadtootaghaj, Saman and Timofte, Radu and Sun, Wei and Zhang, Weixia and Cao, Yuqin and Cao, Linhan and Jia, Jun and Chen, Zijian and Zhang, Zicheng and Min, Xiongkuo and Zhai, Guangtao and Tan, Songbai and Zhang, Lixin and Yue, Guanghui and Kwon, Daekyu and Kim, Dongyoung and Kim, Seon Joo and Zhang, Yunchen and Xu, Xiangkai and Gao, Hong and Bao, Yiming and Shi, Ji and Dong, Xiugang and Zhou, Xiangsheng and Tu, Yaofeng and Chen, Zewen and Xu, Shunhan and Guo, Haochen and Zeng, Yun and Liu, Shuai and Guo, Jian and Wang, Juan and Li, Bing and Liu, Dehua and Liu, Hesong and Malivenko, Grigory and Gerek, Asile and Ma, Xingyuan and Li, Cheng and Lee, Joonhee and Bang, Junseo and Chun, Se Young},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2024},
  pages     = {261-286},
  doi       = {10.1007/978-3-031-91856-8_16},
  url       = {https://mlanthology.org/eccvw/2024/hosu2024eccvw-aim/}
}