2022
DOI: 10.1109/mcg.2020.3026137
|View full text |Cite
|
Sign up to set email alerts
|

Learning Perceptual Aesthetics of 3-D Shapes From Multiple Views

Abstract: The quantification of 3D shape aesthetics has so far focused on specific shape features and manually defined criteria such as the curvature and the rule of thirds respectively. In this paper, we build a model of 3D shape aesthetics directly from human aesthetics preference data and show it to be well aligned with human perception of aesthetics. To build this model, we first crowdsource a large number of human aesthetics preferences by showing shapes in pairs in an online study and then use the same to build a … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
9
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
3
2

Relationship

1
4

Authors

Journals

citations
Cited by 7 publications
(9 citation statements)
references
References 19 publications
0
9
0
Order By: Relevance
“…We used the dataset provided by Dev and Lau [DL22], which contains 277 chairs, 40 tables, 75 mugs, and 88 lamps with 5100, 2875, 825, and 2500 pairwise aesthetics comparisons respectively. We split the data for each shape category by 8:2 for training and testing (denoted as ℐ t ), and we trained with all the categories together.…”
Section: Results and Analysismentioning
confidence: 99%
See 4 more Smart Citations
“…We used the dataset provided by Dev and Lau [DL22], which contains 277 chairs, 40 tables, 75 mugs, and 88 lamps with 5100, 2875, 825, and 2500 pairwise aesthetics comparisons respectively. We split the data for each shape category by 8:2 for training and testing (denoted as ℐ t ), and we trained with all the categories together.…”
Section: Results and Analysismentioning
confidence: 99%
“…Similar to the method from Dev and Lau [DL22], we also consider the margin loss to constrain the pairwise comparison. However, different from their constant margin m , we propose a dynamic margin weighted by “user's agreement”.…”
Section: Methodsmentioning
confidence: 99%
See 3 more Smart Citations