{"id":31211529,"url":"https://github.com/cyberagentailab/graphic-design-evaluation","last_synced_at":"2025-09-21T05:30:44.587Z","repository":{"id":276766739,"uuid":"866399608","full_name":"CyberAgentAILab/Graphic-design-evaluation","owner":"CyberAgentAILab","description":"This is the official repository for \"Can GPTs Evaluate Graphic Design Based on Design Principles?\".","archived":false,"fork":false,"pushed_at":"2025-02-10T09:46:43.000Z","size":98048,"stargazers_count":12,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-10T07:42:49.460Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CyberAgentAILab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-10-02T07:31:32.000Z","updated_at":"2025-05-13T07:38:34.000Z","dependencies_parsed_at":null,"dependency_job_id":"fd1f932e-68ed-4aee-9377-186b8a0668d2","html_url":"https://github.com/CyberAgentAILab/Graphic-design-evaluation","commit_stats":null,"previous_names":["cyberagentailab/graphic-design-evaluation"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CyberAgentAILab/Graphic-design-evaluation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FGraphic-design-evaluation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FGraphic-design-evaluation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FGraphic-design-evaluation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FGraphic-design-evaluation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CyberAgentAILab","download_url":"https://codeload.github.com/CyberAgentAILab/Graphic-design-evaluation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FGraphic-design-evaluation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":276195627,"owners_count":25601152,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-21T02:00:07.055Z","response_time":72,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-09-21T05:30:42.151Z","updated_at":"2025-09-21T05:30:44.564Z","avatar_url":"https://github.com/CyberAgentAILab.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Paper: Can GPTs Evaluate Graphic Design Based on Design Principles?\nDaichi Haraguchi\u003csup\u003e1\u003c/sup\u003e, Naoto Inoue\u003csup\u003e1\u003c/sup\u003e, Wataru Shimoda\u003csup\u003e1\u003c/sup\u003e, Hayato Mitani\u003csup\u003e2\u003c/sup\u003e, Seiichi Uchida\u003csup\u003e2\u003c/sup\u003e, Kota Yamaguchi\u003csup\u003e1\u003c/sup\u003e  \n\u003csup\u003e1\u003c/sup\u003eCyberAgent.Inc, \u003csup\u003e2\u003c/sup\u003e Kyushu University  \nAccepted to SIGGRAPH Asia (Technical Communications Track).\n[[Project-page](https://cyberagentailab.github.io/Graphic-design-evaluation/)]\n\n## Introduction\nThis repository contains the data for \"Can GPTs Evaluate Graphic Design Based on Design Principles?\".\n\n\u003cimg src = \"https://github.com/CyberAgentAILab/Graphic-design-evaluation/blob/projectpage/docs/images/teaser.jpg\" title = \"teaser\" \u003e\n\n## Data\n\u003cpre\u003e\n./GPT_eval_data\n├── gpt_eval\n      ├── gpt_abs_alignment.csv\n      ...\n      └── gpt_comp_whitespace.csv\n├── human_eval_data\n      ├── human_abs_alignment.csv\n      ...\n      └── human_comp_whitespace.csv\n└── images.zip\n\u003c/pre\u003e\nEach CSV file includes the evaluation results.\nFile names consist of \"[eval method]_[eval type]\\_[design principle].csv.\"  \nNote:  \n\"eval. method\" is \"gpt\" or \"human.\"  \n\"eval. type\" is \"abs\" (absolute evaluation) or \"comp\" (comparative (relative) evaluation).  \n\"design principle\" is \"alignment,\" \"overlap,\" or \"whitespace.\"  \n\nExample:  \n\"gpt_abs_alignment.csv\" is the absolute evaluation result by GPT for alignment. \n\n\"images.zip\" includes images.  \nThe structure in the \"images.zip\" is below.\n\u003cpre\u003e\nimages\n├── lefttop_large\n      ├── [image_ID].png\n      ...\n      └── [image_ID].png\n...\n└── org\n      ├── [image_ID].png\n      ...\n      └── [image_ID].png\n\u003c/pre\u003e\n\nNote:  \nThe directory name consists of \"[perturbation element]_[perturbation size]\"  \n\"Org\" includes original images without perturbation.  \nEach image name is an image ID that is written in the CSV files.  \n\n\n\n## The structure of each CSV file\nCSV for absolute evaluation\n| id | perturbation | 0 | 1 | 2 | 3 | 4 | avg |\n| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |\n| image ID | perturbation size | score | score | score | score | score |average score|\n\nCSV for relative evaluation\n| id | comparative | better_design_0 | better_design_1 | better_design_2 | better_design_3 | better_design_4 | voting_res |\n| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |\n| image ID | perturbation size of comparison image | voting result | voting result| voting result | voting result | voting result | aggregation of voting results|\n\n\n## Visualization\nWe provides a notebook for showing results.  \n- `scatter_plot.ipynb` shows the scatter plot between human evaluation and GPT evaluation.  \n\n## Reference\n```bibtex\n@inproceedings{haraguchi2024can,\n  title={Can GPTs Evaluate Graphic Design Based on Design Principles?},\n  author={Haraguchi, Daichi and Inoue, Naoto and Shimoda, Wataru and Mitani, Hayato and Uchida, Seiichi and Yamaguchi, Kota},\n  booktitle={SIGGRAPH Asia 2024 Technical Communications},\n  pages={1--4},\n  year={2024}\n}\n```\n\n## Contact\nThis repository is maintained by Daichi Haraguchi.  \nE-mail: haraguchi_daichi_xa[at]cyberagent.co.jp\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyberagentailab%2Fgraphic-design-evaluation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcyberagentailab%2Fgraphic-design-evaluation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyberagentailab%2Fgraphic-design-evaluation/lists"}