计算机科学 ›› 2024, Vol. 51 ›› Issue (11): 47-53.doi: 10.11896/jsjkx.240700085

• 社交媒体虚假信息检测 • 上一篇    下一篇

针对AIGC数字插画设计原则的用户评价指标分析

徐俊1, 周沛瑾1, 张海静1, 张豪2, 徐育忠1   

  1. 1 浙江工业大学设计与建筑学院 杭州 310000
    2 浙江工业大学计算机与科学技术学院 杭州 310000
  • 收稿日期:2024-07-10 修回日期:2024-08-29 出版日期:2024-11-15 发布日期:2024-11-06
  • 通讯作者: 徐育忠(xuyu70@126.com)
  • 作者简介:(xujun@zjut.edu.com)
  • 基金资助:
    国家社会科学基金(22BMZ038)

Analysis of User Evaluation Indicator for AIGC Digital Illustration Design Principles

XU Jun1, ZHOU Peijin1, ZHANG Haijing1, ZHANG Hao2, XU Yuzhong1   

  1. 1 College of Design and Architecture,Zhejiang University of Technology,Hangzhou 310000,China
    2 College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310000,China
  • Received:2024-07-10 Revised:2024-08-29 Online:2024-11-15 Published:2024-11-06
  • About author:XU Jun,born in 1979,master,senior experimentalist,master’s supervisor,is a premium member of CCF(No.27493S).His main research interests include digital media art and digital humanities.
    XU Yuzhong,born in 1970,master,professor,master’s supervisor.His main research interests include digital media art and design aesthetics.
  • Supported by:
    National Social Science Fundation of China(22BMZ038).

摘要: 针对数字插画设计原则和AIGC技术原理,构建了从文学文本到数字插画的生产流程,并以实验的方式论证了AIGC数字插画的实际效果和存在的问题。梳理了数字插画的发展现状,分析了AIGC与数字插画设计原则之间的关系,归纳介绍了当前AIGC用于数字插画的主要流程和关键技术,然后使用多种AI算法搭建了从文学文本到数字插画的生产流程,并进行了多组实验,最后根据图文契合度等指标设计问卷进行用户评测,分析AIGC数字插画生成的规律和特点及其可用性。AIGC能满足一定的叙事和艺术风格要求,但其效果随着文本叙事性的增强而呈下降趋势,同时对于生僻内容效果不佳,其画面细节无法表现复杂的叙事情景。通过理论分析和实验对比可以得出,AIGC借助人工智能技术在数字插画的生产效率上具有巨大优势,但由于缺乏对叙事内容的理解,其在画面表达上存在不足,目前还依赖于设计者的高度参与来解决实用性问题,同时也需要各方协同来促进新技术的良性发展。

关键词: 数字插画, AIGC, 人工智能, 叙事性

Abstract: Based on the digital illustration design principles and the technical principles of AIGC,a production process from lite-rary text to digital illustration has been constructed.Through experiments,the actual effects and existing problems of AIGC digi-tal illustration have been demonstrated.The current development status of digital illustration has been reviewed,and the relationship between AIGC and digital illustration design principles has been analyzed.The main processes and key technologies currently used for digital illustration with AIGC have been summarized and introduced.Then,multiple AI algorithms have been used to build a production process from literary text to digital illustration,and multiple sets of experiments have been conducted.Finally,a questionnaire has been designed based on indicators such as the degree of fit between text and image to evaluate users,and analyze the generation rules,characteristics,and usability of AIGC digital illustration.AIGC can meet certain narrative and artistic style requirements,but its effectiveness decreases as the narrative nature of the text increases.At the same time,it has poor performance for rare content,and its image details cannot represent complex narrative scenarios.Through theoretical analysis and experimental comparison,it can be concluded that AIGC has great advantages in terms of production efficiency with the help of artificial intelligence technology in digital illustration.However,due to a lack of understanding of narrative content,there are shortcomings in its image expression.Currently,it still relies on the high involvement of designers to solve practical problems,and it also requires collaboration from all parties to promote the healthy development of new technologies.

Key words: Digital illustration, Artificial intelligence generated content, Artificial intelligence, Narrative

中图分类号: 

  • TP391.41
[1] LIU T.The Construction and Production of Cultural Imagery:An Analysis of the Psychological Operation Mechanism of Vi-sual Rhetoric[J].Modern Communication,2011(9):20-25.
[2] SHI Y.Communication and Thinking of Visual Language in the Image Age[J].Media,2015,209(12):69-71.
[3] WANG S C,PANG H,XIONG Y R,et al.Image Digital Intelli-gence:Phenomenon and Its Interpretation[J].Zhejiang Social Sciences,2023(3):84-93,159.
[4] XIA Z N,CHEN Z L.Cihai[M].Shanghai:Shanghai Dictionary Press,2009:233.
[5] YAO H.Illustration Analysis and Rheological Investigation[J].Nanjing University of the Arts(Art and Design Edition),2011(5):83-85,177.
[6] CHEN Q.On the Art of Illustration in the Digital Age[J].Shanxi Normal University(Philosophy and Social Sciences Edition),2007(S2):158-160.
[7] WANG J H,WANG W L.Research on Modern Digital Illustration[J].Art Education Research,2018(14):16-17.
[8] Artificial Intelligence Generated Content (AIGC) white paper(2022)[EB/OL].[2022-09-04].http://www.cbdio.com/BigData/2022-09/04/content_6170457.htm.
[9] GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Ge-nerative Adversarial Networks[J].Communications of the ACM,2020,63(11):139-144.
[10] HO J,JAIN A,ABBEEL P.Denoising Diffusion ProbabilisticModels[J].Advances in Neural Information Processing Systems,2020,33:6840-6851.
[11] Garnter.Generative AI,Machine Customers and AR/VR areExpected to Transform Sales in the Next Five Years[EB/OL].[2022-11-05].https://www.gartner.com/en/newsroom/press-releases/2022-10-10-gartner-identifies-seven-technology-disruptions-that-willimpact-sales-through-2027.
[12] ZHANG Y.Narrative Illustration Creation of Folk Tale Theme[D].Hangzhou:Zhejiang Sci-Tech University,2019.
[13] LAWRENCE Z.What is Illustration Design?[M].China Youth Publishing House,2011.
[14] HE G M.A Review of Domestic Image Narrative Research Since the 21st Century(I)[J].Journal of Hubei Institute of Fine Arts,2018(4):49-58.
[15] LIU T,WU Y,WANG K Z.Automated Digest Review[J].Information Science,1998(1):65-71.
[16] GONG S.Research on Text Representation of Extractive Multi-Document Abstract[D].Beijing:Beijing Jiaotong University,2013.
[17] MOHAN M J,SUNITHA C,GANESH A,et al.A Study on Ontology Based Abstractive Summarization[J].Procedia Computer Science,2016,87:32-37.
[18] JIANG M.Research on Hand-drawn Illustration Creation Based on Emotional Design Theory[D].Wuhan:Hubei University of Technology,2021.
[19] TAN C P.Review of Fine-grained Sentiment Analysis of Text[J].Journal of University Libraries,2022,43(4):85-99,119.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!