{"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/viescore-towards-explainable-metrics-for","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","arxiv_id":"2312.14867","date":"2023-12-22","proceeding":null,"authors":["Max Ku","Dongfu Jiang","Cong Wei","Xiang Yue","Wenhu Chen"],"abstract":"In the rapidly advancing field of conditional image generation research, challenges such as limited explainability lie in effectively evaluating the performance and capabilities of various models. This paper introduces VIEScore, a Visual Instruction-guided Explainable metric for evaluating any conditional image generation tasks. VIEScore leverages general knowledge from Multimodal Large Language Models (MLLMs) as the backbone and does not require training or fine-tuning. We evaluate VIEScore on seven prominent tasks in conditional image tasks and found: (1) VIEScore (GPT4-o) achieves a high Spearman correlation of 0.4 with human evaluations, while the human-to-human correlation is 0.45. (2) VIEScore (with open-source MLLM) is significantly weaker than GPT-4o and GPT-4v in evaluating synthetic images. (3) VIEScore achieves a correlation on par with human ratings in the generation tasks but struggles in editing tasks. With these results, we believe VIEScore shows its great potential to replace human judges in evaluating image synthesis tasks.","url_abs":"https://arxiv.org/abs/2312.14867v2","url_pdf":"https://arxiv.org/pdf/2312.14867v2.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":"viescore-towards-explainable-metrics-for","repo_url":"https://github.com/TIGER-AI-Lab/VIEScore","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2312.14867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14867"}},"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/TIGER-AI-Lab/VIEScore","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran":9,"unverified":1},"by_repo_kind":{"official":{"samples":11,"ran":10,"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":0,"samples":[{"code_sha256_prefix":"f41cb1a19b154297","entry":"encode_image","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/mllm_tools/openai.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/mllm_tools/openai.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f41cb1a19b154297"}},{"code_sha256_prefix":"5ea35c6f48bf72a0","entry":"fix_json","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/utils.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ea35c6f48bf72a0"}},{"code_sha256_prefix":"e71f0a1840318cb9","entry":"get_api_key","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/mllm_tools/openai.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/mllm_tools/openai.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e71f0a1840318cb9"}},{"code_sha256_prefix":"ae1444e80f1dbb62","entry":"get_file_path","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"paper_implementation/clean_result.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/paper_implementation/clean_result.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae1444e80f1dbb62"}},{"code_sha256_prefix":"0ec33995a5dc05d1","entry":"load_image","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/mllm_tools/utils.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/mllm_tools/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ec33995a5dc05d1"}},{"code_sha256_prefix":"3c0709cacb35e6aa","entry":"load_images","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/mllm_tools/utils.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/mllm_tools/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c0709cacb35e6aa"}},{"code_sha256_prefix":"c302d46717895f2b","entry":"pick_next_item","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/mllm_tools/openai.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/mllm_tools/openai.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c302d46717895f2b"}},{"code_sha256_prefix":"ad84f742a5662dd6","entry":"pil_image_to_base64","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/mllm_tools/utils.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/mllm_tools/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad84f742a5662dd6"}},{"code_sha256_prefix":"22ae1ae2b156c6ff","entry":"read_file_to_string","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/utils.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22ae1ae2b156c6ff"}},{"code_sha256_prefix":"ff84253d325511bc","entry":"read_files_to_string","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/utils.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ff84253d325511bc"}},{"code_sha256_prefix":"65ffcd17f0ae0bab","entry":"save_image_from_url","repo":"TIGER-AI-Lab/VIEScore","repo_kind":"official","path":"viescore/mllm_tools/gemini.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/mllm_tools/gemini.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65ffcd17f0ae0bab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}