Loading...
You can consult and search here for all Inria publications on HAL or on HAL-Inria.
This list of publications is automatically generated each night.
If at least one of the authors of the publication is associated with Inria, it will be included in this collection. Here to deposit HAL-Inria
Contact : archive-ouverte@inria.fr
Open Access
75 %
The latest publications
-
-
-
-
-
-
-
-
-
-
-
-
-
Baptiste Chopin, Hao Tang, Mohamed Daoudi. Bipartite Graph Diffusion Model for Human Interaction Generation: The generation of natural human motion interactions is a hot topic in computer vision and computer animation. It is a challenging task due to the diversity of possible human motion interactions. Diffusion models, which have already shown remarkable generative capabilities in other domains, are a good candidate for this task. In this paper, we introduce a novel bipartite graph diffusion method (BiGraphDiff) to generate human motion interactions between two persons. Specifically, bipartite node sets are constructed to model the inherent geometric constraints between skeleton nodes during interactions. The interaction graph diffusion model is transformer-based, combining some state-of-the-art motion methods. We show that the proposed achieves new state-of-the-art results on leading benchmarks for the human interaction generation task.. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024, Jan 2024, WAIKOLOA, HI, United States. ⟨hal-04274209⟩
Number of full text documents
73 665
Notices
0
Keywords
73 481
Publications with fulltext
48
Research data
106
Softwares