{"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/exploring-clip-for-assessing-the-look-and","title":"Exploring CLIP for Assessing the Look and Feel of Images","arxiv_id":"2207.12396","date":"2022-07-25","proceeding":null,"authors":["Jianyi Wang","Kelvin C. K. Chan","Chen Change Loy"],"abstract":"Measuring the perception of visual content is a long-standing problem in computer vision. Many mathematical models have been developed to evaluate the look or quality of an image. Despite the effectiveness of such tools in quantifying degradations such as noise and blurriness levels, such quantification is loosely coupled with human language. When it comes to more abstract perception about the feel of visual content, existing methods can only rely on supervised models that are explicitly trained with labeled data collected via laborious user study. In this paper, we go beyond the conventional paradigms by exploring the rich visual language prior encapsulated in Contrastive Language-Image Pre-training (CLIP) models for assessing both the quality perception (look) and abstract perception (feel) of images in a zero-shot manner. In particular, we discuss effective prompt designs and show an effective prompt pairing strategy to harness the prior. We also provide extensive experiments on controlled datasets and Image Quality Assessment (IQA) benchmarks. Our results show that CLIP captures meaningful priors that generalize well to different perceptual assessments. Code is avaliable at https://github.com/IceClear/CLIP-IQA.","url_abs":"https://arxiv.org/abs/2207.12396v2","url_pdf":"https://arxiv.org/pdf/2207.12396v2.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":"exploring-clip-for-assessing-the-look-and","repo_url":"https://github.com/iceclear/clip-iqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"},{"task_slug":"no-reference-image-quality-assessment","task_name":"No-Reference Image Quality Assessment"},{"task_slug":"video-quality-assessment","task_name":"Video Quality Assessment"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/no-reference-image-quality-assessment-on-uhd","task":"No-Reference Image Quality Assessment","dataset":"UHD-IQA","model":"CLIP-IQA+","rank_in_archive_order":3,"of":7,"metrics":{"PLCC":"0.709","SRCC":"0.747"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"ClipIQA+ ResNet50","rank_in_archive_order":9,"of":60,"metrics":{"KLCC":"0.52628","PLCC":"0.65154","SROCC":"0.65713","Type":"NR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"ClipIQA","rank_in_archive_order":17,"of":60,"metrics":{"KLCC":"0.49417","PLCC":"0.58944","SROCC":"0.60808","Type":"NR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"ClipIQA+","rank_in_archive_order":25,"of":60,"metrics":{"KLCC":"0.69774","PLCC":"0.71808","SROCC":"0.56875","Type":"NR"},"uses_additional_data":false},{"leaderboard":"/sota/video-quality-assessment-on-msu-sr-qa-dataset","task":"Video Quality Assessment","dataset":"MSU SR-QA Dataset","model":"ClipIQA+ ViT-L-14","rank_in_archive_order":37,"of":60,"metrics":{"KLCC":"0.38794","PLCC":"0.50379","SROCC":"0.49881","Type":"NR"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.12396","atlas_url":"https://app.syntology.ai/?focus=2207.12396","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}