{"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/a-comprehensive-study-of-multimodal-large","title":"A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment","arxiv_id":"2403.10854","date":"2024-03-16","proceeding":null,"authors":["Tianhe Wu","Kede Ma","Jie Liang","Yujiu Yang","Lei Zhang"],"abstract":"While Multimodal Large Language Models (MLLMs) have experienced significant advancement in visual understanding and reasoning, their potential to serve as powerful, flexible, interpretable, and text-driven models for Image Quality Assessment (IQA) remains largely unexplored. In this paper, we conduct a comprehensive and systematic study of prompting MLLMs for IQA. We first investigate nine prompting systems for MLLMs as the combinations of three standardized testing procedures in psychophysics (i.e., the single-stimulus, double-stimulus, and multiple-stimulus methods) and three popular prompting strategies in natural language processing (i.e., the standard, in-context, and chain-of-thought prompting). We then present a difficult sample selection procedure, taking into account sample diversity and uncertainty, to further challenge MLLMs equipped with the respective optimal prompting systems. We assess three open-source and one closed-source MLLMs on several visual attributes of image quality (e.g., structural and textural distortions, geometric transformations, and color differences) in both full-reference and no-reference scenarios. Experimental results show that only the closed-source GPT-4V provides a reasonable account for human perception of image quality, but is weak at discriminating fine-grained quality variations (e.g., color differences) and at comparing visual quality of multiple images, tasks humans can perform effortlessly.","url_abs":"https://arxiv.org/abs/2403.10854v3","url_pdf":"https://arxiv.org/pdf/2403.10854v3.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":"a-comprehensive-study-of-multimodal-large","repo_url":"https://github.com/tianhewu/mllms-for-iqa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-comprehensive-study-of-multimodal-large","repo_url":"https://github.com/tianhewu/visualquality-r1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-quality-assessment","task_name":"Image Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.10854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10854"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tianhewu/mllms-for-iqa","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tianhewu/visualquality-r1","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"72743db77d429657","entry":"calculate_mse","repo":"tianhewu/mllms-for-iqa","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tianhewu/mllms-for-iqa/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"72743db77d429657"}},{"code_sha256_prefix":"8ae2250327f7c2b3","entry":"calculate_plcc","repo":"tianhewu/mllms-for-iqa","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tianhewu/mllms-for-iqa/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ae2250327f7c2b3"}},{"code_sha256_prefix":"835b6d8b5cd46279","entry":"calculate_srcc","repo":"tianhewu/mllms-for-iqa","repo_kind":"official","path":"utils.py","file_url":"https://github.com/tianhewu/mllms-for-iqa/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"835b6d8b5cd46279"}},{"code_sha256_prefix":"31b79fcafbcf9f64","entry":"dialogue_with_check","repo":"tianhewu/mllms-for-iqa","repo_kind":"official","path":"iqa_models/gpt4v.py","file_url":"https://github.com/tianhewu/mllms-for-iqa/blob/HEAD/iqa_models/gpt4v.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"31b79fcafbcf9f64"}},{"code_sha256_prefix":"dc45f09a71c093c6","entry":"execute_with_timeout","repo":"tianhewu/mllms-for-iqa","repo_kind":"official","path":"iqa_models/gpt4v.py","file_url":"https://github.com/tianhewu/mllms-for-iqa/blob/HEAD/iqa_models/gpt4v.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dc45f09a71c093c6"}},{"code_sha256_prefix":"be1713dda908b70b","entry":"extract_floats_from_string","repo":"tianhewu/mllms-for-iqa","repo_kind":"official","path":"iqa_models/gpt4v.py","file_url":"https://github.com/tianhewu/mllms-for-iqa/blob/HEAD/iqa_models/gpt4v.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be1713dda908b70b"}},{"code_sha256_prefix":"0ed0bc77cad17572","entry":"get_prompt","repo":"tianhewu/mllms-for-iqa","repo_kind":"official","path":"prompts/gpt4v_prompt.py","file_url":"https://github.com/tianhewu/mllms-for-iqa/blob/HEAD/prompts/gpt4v_prompt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ed0bc77cad17572"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}