Computational aesthetics analyzes various expressions arising in art and music works from an aesthetic perspective, and strives to utilize them for the purpose of re-synthesis. Evaluation of such diverse expressions, including exaggeration and omission, is not unified; it does change depending on the intention of the creator and the taste of a person who appreciates the work. This team pursues computational approaches to identification of aesthetic elements.
Members
 ：April enrollment |  ：September enrollment |  ：Team leader |
Research themes
Visual analysis of leading lines based on differential topology
Suspended themes
Portraits (2023―2024)
Generation of complementary background images for portrait illustrations using interactive genetic algorithm
(2022―2023)
A house dance design system
based on constructive choreographic process
Retouching (2021―2022)
Photo retouching for mixed painting material style in digital illustrations
(2020―2021)
Gernerating naturally animated crowd scenes with non-player characters based on arousal-valence model
(2019―2021)
Automatic generation of 3D natural Anime-like non-player characters with machine learning
