Bipartite Graph Diffusion Model for Human Interaction Generation

1 code implementation • 24 Jan 2023 • Baptiste Chopin, Hao Tang, Mohamed Daoudi

The generation of natural human motion interactions is a hot topic in computer vision and computer animation.

Interaction Transformer for Human Reaction Generation

1 code implementation • 4 Jul 2022 • Baptiste Chopin, Hao Tang, Naima Otberdout, Mohamed Daoudi, Nicu Sebe

To address this limitation, we propose a novel interaction Transformer (InterFormer) consisting of a Transformer network with both temporal and spatial attention.

3D Skeleton-based Human Motion Prediction with Manifold-Aware GAN

no code implementations • 1 Mar 2022 • Baptiste Chopin, Naima Otberdout, Mohamed Daoudi, Angela Bartolo

Using such a compact representation avoids error accumulation and provides robust representation for long-term prediction while ensuring the smoothness and the coherence of the whole motion.

Human motion prediction motion prediction

Human Motion Prediction Using Manifold-Aware Wasserstein GAN

no code implementations • 18 May 2021 • Baptiste Chopin, Naima Otberdout, Mohamed Daoudi, Angela Bartolo

Human motion prediction aims to forecast future human poses given a prior pose sequence.

Human motion prediction motion prediction