An Exploratory Study of Kansei-Guided Reference Matching for Automotive Side-View Sketch Rendering

To provide a systematic basis for selecting style references for automotive side-view sketches, this study presents a concept rendering workflow guided by Kansei attribute matching. The workflow ranks candidate references using ratings on six bipolar Kansei attributes and generates renderings by interpolating StyleGAN latent codes. For all six sketches, Pearson correlation and Euclidean distance identified the same top-ranked reference. Compared with renderings based on references chosen by the sketch authors, renderings based on Kansei-matched references received, on average, more fixations and longer total fixation durations in both sketch groups. Changes in author satisfaction varied across cases. ControlNet and IP-Adapter provided a supplementary comparison using the same inputs. The study offers a reference selection method whose rankings can be checked, and it demonstrates how the selected references can inform automotive concept rendering.

Authors

Institutions

Publication Details

Journal
Information
Published
2026-11-18
DOI
https://doi.org/10.3390/info17111172
Primary Topic
Color perception and design
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

An Exploratory Study of Kansei-Guided Reference Matching for Automotive Side-View Sketch Rendering

Junqiang Zheng, ZhengGen Deng, Qipeng Chen, Qiang Bai et al.
2 links
Information
Color perception and design
article

An Exploratory Study of Kansei-Guided Reference Matching for Automotive Side-View Sketch Rendering

Junqiang Zheng, ZhengGen Deng, Qipeng Chen, Qiang Bai, Tao Hu
article en

Abstract

To provide a systematic basis for selecting style references for automotive side-view sketches, this study presents a concept rendering workflow guided by Kansei attribute matching. The workflow ranks candidate references using ratings on six bipolar Kansei attributes and generates renderings by interpolating StyleGAN latent codes. For all six sketches, Pearson correlation and Euclidean distance identified the same top-ranked reference. Compared with renderings based on references chosen by the sketch authors, renderings based on Kansei-matched references received, on average, more fixations and longer total fixation durations in both sketch groups. Changes in author satisfaction varied across cases. ControlNet and IP-Adapter provided a supplementary comparison using the same inputs. The study offers a reference selection method whose rankings can be checked, and it demonstrates how the selected references can inform automotive concept rendering.

InformationVol. 17(11)
Guiyang University (CN)
Guizhou Science and Technology Department, Guiyang University
Color perception and design
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon