In this work, we investigate a simple and must-known conditional generative framework
based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained …

Dance is an important human art form, but creating new dances can be difficult and time-
consuming. In this work, we introduce Editable Dance GEneration (EDGE), a state-of-the-art …

We present a novel method for populating 3D indoor scenes with virtual humans that can
navigate in the environment and interact with objects in a realistic manner. Existing …

Our goal is to synthesize 3D human motions given textual inputs describing simultaneous
actions, for examplewaving hand'whilewalking'at the same time. We refer to generating such …

Traditional handcrafted animation often heavily relies on creating keyframes while the in-
betweening is automatically generated through spline-based interpolation. Animators have …

We study a challenging task: text-to-motion synthesis, aiming to generate motions that align
with textual descriptions and exhibit coordinated movements. Currently, the part-based …

The gradual nature of a diffusion process that synthesizes samples in small increments
constitutes a key ingredient of Denoising Diffusion Probabilistic Models (DDPM), which have …

Recently, methods for skeleton-based human activity recognition have been shown to be
vulnerable to adversarial attacks. However, these attack methods require either the full …

Abstract We introduce the Multi-Motion Discrete Diffusion Models (M2D2M), a novel
approach for human motion generation from textual descriptions of multiple actions, utilizing …

We present a method to animate a character incorporating multiple part-wise motion priors
(PMP). While previous works allow creating realistic articulated motions from reference data …