智能设计人员与中级设计人员设计质量与效率的比较

2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC) Pub Date : 2022-08-01 DOI:10.1109/IHMSC55436.2022.00050

Jiang Xu, Han Lu

{"title":"智能设计人员与中级设计人员设计质量与效率的比较","authors":"Jiang Xu, Han Lu","doi":"10.1109/IHMSC55436.2022.00050","DOIUrl":null,"url":null,"abstract":"Design intelligence is to adapt and introduce artificial intelligence methods to design tasks. SmartPaint is a typical design intelligence system to generate paintings, and its improved version further considers the causal relation between objects in a scene and is trained with a larger dataset with over one million artwork samples. In this paper, we compare the improved SmartPaint with 12 intermediate designers on a controlled painting task. The intermediate designers have been working in the design and related industries for over two years. The comparison is about design quality and efficiency, evaluated by 20 volunteers. Empirically we find over 50% of the paintings generated by SmartPaint are more preferred than those drawn by human designers along creativity, artistic quality and color scheme. Besides, SmartPaint takes only less than 1% of the time spended by human designers.","PeriodicalId":447862,"journal":{"name":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Comparing the Design Quality and Efficiency between Design Intelligence and Intermediate Designers\",\"authors\":\"Jiang Xu, Han Lu\",\"doi\":\"10.1109/IHMSC55436.2022.00050\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Design intelligence is to adapt and introduce artificial intelligence methods to design tasks. SmartPaint is a typical design intelligence system to generate paintings, and its improved version further considers the causal relation between objects in a scene and is trained with a larger dataset with over one million artwork samples. In this paper, we compare the improved SmartPaint with 12 intermediate designers on a controlled painting task. The intermediate designers have been working in the design and related industries for over two years. The comparison is about design quality and efficiency, evaluated by 20 volunteers. Empirically we find over 50% of the paintings generated by SmartPaint are more preferred than those drawn by human designers along creativity, artistic quality and color scheme. Besides, SmartPaint takes only less than 1% of the time spended by human designers.\",\"PeriodicalId\":447862,\"journal\":{\"name\":\"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)\",\"volume\":\"25 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IHMSC55436.2022.00050\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IHMSC55436.2022.00050","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

设计智能是将人工智能方法引入设计任务中。SmartPaint是一个典型的设计智能系统来生成绘画，其改进版本进一步考虑了场景中物体之间的因果关系，并使用超过一百万件艺术品样本的更大数据集进行训练。在本文中，我们将改进的SmartPaint与12个中级设计人员在受控绘画任务上进行比较。中级设计师在设计及相关行业工作两年以上。20名志愿者对设计质量和效率进行了比较。根据经验，我们发现超过50%的由SmartPaint生成的画作在创造力、艺术品质和配色方案方面比人类设计师绘制的画作更受欢迎。此外，SmartPaint只花费不到人类设计师1%的时间。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Comparing the Design Quality and Efficiency between Design Intelligence and Intermediate Designers

Design intelligence is to adapt and introduce artificial intelligence methods to design tasks. SmartPaint is a typical design intelligence system to generate paintings, and its improved version further considers the causal relation between objects in a scene and is trained with a larger dataset with over one million artwork samples. In this paper, we compare the improved SmartPaint with 12 intermediate designers on a controlled painting task. The intermediate designers have been working in the design and related industries for over two years. The comparison is about design quality and efficiency, evaluated by 20 volunteers. Empirically we find over 50% of the paintings generated by SmartPaint are more preferred than those drawn by human designers along creativity, artistic quality and color scheme. Besides, SmartPaint takes only less than 1% of the time spended by human designers.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2022 14th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)

自引率

0.00%

发文量