Interaction Mix and Match: Synthesizing Close Interaction using Conditional Hierarchical GAN with Multi-Hot Class Embedding

dc.contributor.authorGoel, Amanen_US
dc.contributor.authorMen, Qianhuien_US
dc.contributor.authorHo, Edmond S. L.en_US
dc.contributor.editorDominik L. Michelsen_US
dc.contributor.editorSoeren Pirken_US
dc.date.accessioned2022-08-10T15:20:05Z
dc.date.available2022-08-10T15:20:05Z
dc.date.issued2022
dc.description.abstractSynthesizing multi-character interactions is a challenging task due to the complex and varied interactions between the characters. In particular, precise spatiotemporal alignment between characters is required in generating close interactions such as dancing and fighting. Existing work in generating multi-character interactions focuses on generating a single type of reactive motion for a given sequence which results in a lack of variety of the resultant motions. In this paper, we propose a novel way to create realistic human reactive motions which are not presented in the given dataset by mixing and matching different types of close interactions. We propose a Conditional Hierarchical Generative Adversarial Network with Multi-Hot Class Embedding to generate the Mix and Match reactive motions of the follower from a given motion sequence of the leader. Experiments are conducted on both noisy (depth-based) and high-quality (MoCap-based) interaction datasets. The quantitative and qualitative results show that our approach outperforms the state-of-the-art methods on the given datasets. We also provide an augmented dataset with realistic reactive motions to stimulate future research in this area.en_US
dc.description.number8
dc.description.sectionheadersLearning
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14647
dc.identifier.issn1467-8659
dc.identifier.pages327-338
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14647
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14647
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies --> Motion capture; Machine learning; Motion processing; Animation
dc.subjectComputing methodologies
dc.subjectMotion capture
dc.subjectMachine learning
dc.subjectMotion processing
dc.subjectAnimation
dc.titleInteraction Mix and Match: Synthesizing Close Interaction using Conditional Hierarchical GAN with Multi-Hot Class Embeddingen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
v41i8pp327-338.pdf
Size:
13.69 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
sca_2022_supplementalmaterial_8156.mp4
Size:
61.02 MB
Format:
Unknown data format
Collections