Denoising diffusion models hold great promise for generating diverse and realistic human
motions. However, existing motion diffusion models largely disregard the laws of physics in …

We propose CG-HOI the first method to address the task of generating dynamic 3D human-
object interactions (HOIs) from text. We model the motion of both human and object in an …

The generation of stylistic 3D facial animations driven by speech presents a significant
challenge as it requires learning a many-to-many map** between speech, style, and the …

Abstract We introduce Motion2VecSets a 4D diffusion model for dynamic surface
reconstruction from point cloud sequences. While existing state-of-the-art methods have …

Abstract We propose Neural 3D Articulated object Prior (NAP), the first 3D deep generative
model to synthesize 3D articulated object models. Despite the extensive research on …

The zero-shot open-vocabulary setting poses challenges for image classification.
Fortunately, utilizing a vision-language model like CLIP, pre-trained on image-textpairs …

Music-driven group choreography poses a considerable challenge but holds significant
potential for a wide range of industrial applications. The ability to generate synchronized and …

Generating realistic human motion sequences from text descriptions is a challenging task
that requires capturing the rich expressiveness of both natural language and human motion …