{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lar-iqa-a-lightweight-accurate-and-robust-no","title":"LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model","arxiv_id":"2408.17057","date":"2024-08-30","proceeding":null,"authors":["Nasim Jamshidi Avanaki","Abhijay Ghildyal","Nabajeet Barman","Saman Zadtootaghaj"],"abstract":"Recent advancements in the field of No-Reference Image Quality Assessment (NR-IQA) using deep learning techniques demonstrate high performance across multiple open-source datasets. However, such models are typically very large and complex making them not so suitable for real-world deployment, especially on resource- and battery-constrained mobile devices. To address this limitation, we propose a compact, lightweight NR-IQA model that achieves state-of-the-art (SOTA) performance on ECCV AIM UHD-IQA challenge validation and test datasets while being also nearly 5.7 times faster than the fastest SOTA model. Our model features a dual-branch architecture, with each branch separately trained on synthetically and authentically distorted images which enhances the model's generalizability across different distortion types. To improve robustness under diverse real-world visual conditions, we additionally incorporate multiple color spaces during the training process. We also demonstrate the higher accuracy of recently proposed Kolmogorov-Arnold Networks (KANs) for final quality regression as compared to the conventional Multi-Layer Perceptrons (MLPs). Our evaluation considering various open-source datasets highlights the practical, high-accuracy, and robust performance of our proposed lightweight model. Code: https://github.com/nasimjamshidi/LAR-IQA.","url_abs":"https://arxiv.org/abs/2408.17057v2","url_pdf":"https://arxiv.org/pdf/2408.17057v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lar-iqa-a-lightweight-accurate-and-robust-no","repo_url":"https://github.com/nasimjamshidi/lar-iqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"kolmogorov-arnold-networks","task_name":"Kolmogorov-Arnold Networks"},{"task_slug":"no-reference-image-quality-assessment","task_name":"No-Reference Image Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/no-reference-image-quality-assessment-on-uhd","task":"No-Reference Image Quality Assessment","dataset":"UHD-IQA","model":"LAR-IQA (KAN head)","rank_in_archive_order":1,"of":7,"metrics":{"PLCC":"0.786","SRCC":"0.836"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}