基于扩散模型的SUV汽车前脸风格意象研究
李依璟1，吴银奎*,2，滕伟杭1，熊艳1
（1.四川大学 机械工程学院，四川 成都 610065；2.绵阳职业技术学院 智能制造学院，四川 绵阳 621000）
摘要：人工智能的最新进展正在带来一种变革性的AI驱动的产品设计方法，对许多行业产生重大影响。本文提出了一种基于运动型多用途车前脸风格意象的情感设计方法，利用扩散模型辅助生成新的造型方案，通过眼动追踪技术对生成的样本进行评估，旨在帮助设计师了解AI驱动模式下，代表不同风格意象的SUV汽车融合后，消费者对融合前后样本前脸特征关注的重点。实验结果表明：（1）有无格栅的设计会影响被试者对“时尚的”的意象感知；（2）格栅样式会影响“沉稳的”和“科技的”感知，有边框的格栅促进“沉稳的”感知，无边框格栅更易感知到“科技的”意象；（3）上扬的特征线和细长上扬的前车灯促进“时尚的”意象感知。研究结果为基于AI驱动设计不同风格产品提供了一个新的思路，增加对人工智能应用于产品设计的理解。
关键词：人工智能；扩散模型；SUV前脸设计；风格意象；造型特征
中图分类号：TP18 文献标志码：A doi：10.3969/j.issn.1006-0316.2024.03.011
文章编号：1006-0316 (2024) 03-0074-07
Front Face Style Image of SUVs Based on Diffusion Models
LI Yijing1，WU Yinkui2，TENG Weihang1，XIONG Yan1
( 1. School of Mechanical Engineering, Sichuan University, Chengdu 610065, China；2. Institute of Intelligent Manufacturing, MianYang Polytechnic, Mianyang 621000, China )
Abstract：The latest advancements in AI are ushering in a revolutionary AI-driven approach to product design, significantly impacting various industries. This paper introduces an emotion-based design method for the front face style image of SUV, utilizing diffusion models to assist in generating new styling options. The method incorporates eye-tracking technology to evaluate the generated samples, aiming to aid designers in understanding consumer focus on the front face features of SUV with different style images before and after AI-driven amalgamation. The experimental results indicate that (1) the presence or absence of a grille influences the perception of a “fashionable” image; (2) grille style affects the perception of “steady” and “technological” images, with framed grilles enhancing the “steady” perception, and frameless grilles leading to a stronger “technological” image; and (3) uplifted feature lines and slender, upward front headlights promote the perception of a “fashionable” image. The findings offer a novel approach to AI-driven design of various style products and enhance the understanding of AI applications in product design.
Key words：artificial intelligence；diffusion model；SUV front face design；style image；styling features
———————————————
收稿日期：2023-10-10
作者简介：李依璟（1999－），女，云南楚雄人，硕士研究生，主要研究方向为工业设计，E-mail：joyce778x@gmail.com。
*通讯作者：吴银奎（1982－），男，新疆伊犁人，硕士，讲师，主要研究方向为产品创新设计理论，E-mail：wuyinkui@163.com。
（1.四川大学 机械工程学院，四川 成都 610065；2.绵阳职业技术学院 智能制造学院，四川 绵阳 621000）
摘要：人工智能的最新进展正在带来一种变革性的AI驱动的产品设计方法，对许多行业产生重大影响。本文提出了一种基于运动型多用途车前脸风格意象的情感设计方法，利用扩散模型辅助生成新的造型方案，通过眼动追踪技术对生成的样本进行评估，旨在帮助设计师了解AI驱动模式下，代表不同风格意象的SUV汽车融合后，消费者对融合前后样本前脸特征关注的重点。实验结果表明：（1）有无格栅的设计会影响被试者对“时尚的”的意象感知；（2）格栅样式会影响“沉稳的”和“科技的”感知，有边框的格栅促进“沉稳的”感知，无边框格栅更易感知到“科技的”意象；（3）上扬的特征线和细长上扬的前车灯促进“时尚的”意象感知。研究结果为基于AI驱动设计不同风格产品提供了一个新的思路，增加对人工智能应用于产品设计的理解。
关键词：人工智能；扩散模型；SUV前脸设计；风格意象；造型特征
中图分类号：TP18 文献标志码：A doi：10.3969/j.issn.1006-0316.2024.03.011
文章编号：1006-0316 (2024) 03-0074-07
Front Face Style Image of SUVs Based on Diffusion Models
LI Yijing1，WU Yinkui2，TENG Weihang1，XIONG Yan1
( 1. School of Mechanical Engineering, Sichuan University, Chengdu 610065, China；2. Institute of Intelligent Manufacturing, MianYang Polytechnic, Mianyang 621000, China )
Abstract：The latest advancements in AI are ushering in a revolutionary AI-driven approach to product design, significantly impacting various industries. This paper introduces an emotion-based design method for the front face style image of SUV, utilizing diffusion models to assist in generating new styling options. The method incorporates eye-tracking technology to evaluate the generated samples, aiming to aid designers in understanding consumer focus on the front face features of SUV with different style images before and after AI-driven amalgamation. The experimental results indicate that (1) the presence or absence of a grille influences the perception of a “fashionable” image; (2) grille style affects the perception of “steady” and “technological” images, with framed grilles enhancing the “steady” perception, and frameless grilles leading to a stronger “technological” image; and (3) uplifted feature lines and slender, upward front headlights promote the perception of a “fashionable” image. The findings offer a novel approach to AI-driven design of various style products and enhance the understanding of AI applications in product design.
Key words：artificial intelligence；diffusion model；SUV front face design；style image；styling features
———————————————
收稿日期：2023-10-10
作者简介：李依璟（1999－），女，云南楚雄人，硕士研究生，主要研究方向为工业设计，E-mail：joyce778x@gmail.com。
*通讯作者：吴银奎（1982－），男，新疆伊犁人，硕士，讲师，主要研究方向为产品创新设计理论，E-mail：wuyinkui@163.com。
设为首页 | 加入收藏 | 免责条款
《机械》杂志版权所有 Copyright©2008-2012 Jixiezazhi.com All Rights Reserved
电话：028-85925070 传真：028-85925073 E-mail：jixie@vip.163.com
地址：四川省成都锦江工业开发区墨香路48号 邮编：610063
Powered by PageAdmin CMS