Automated generation of 3D human motions from text is a challenging problem. The
generated motions are expected to be sufficiently diverse to explore the text-grounded …

We introduce MotionCLIP, a 3D human motion auto-encoder featuring a latent embedding
that is disentangled, well behaved, and supports highly semantic textual descriptions …

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 …

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 …

Large-scale pre-trained Vision & Language (VL) models have shown remarkable
performance in many applications, enabling replacing a fixed set of supported classes with …

We present a novel approach named OmniControl for incorporating flexible spatial control
signals into a text-conditioned human motion generation model based on the diffusion …

This work targets a novel text-driven whole-body motion generation task, which takes a
given textual description as input and aims at generating high-quality, diverse, and coherent …

Given its wide applications, there is increasing focus on generating 3D human motions from
textual descriptions. Differing from the majority of previous works, which regard actions as …

Text-to-motion generation is an emerging and challenging problem, which aims to
synthesize motion with the same semantics as the input text. However, due to the lack of …

The emergence of neural networks has revolutionized the field of motion synthesis. Yet,
learning to unconditionally synthesize motions from a given distribution remains …