Synthesizing semantic-aware, long-horizon, human-object interaction is critical to simulate
realistic human behaviors. In this work, we address the challenging problem of generating …

Human motion generation, a cornerstone technique in animation and video production, has
widespread applications in various tasks like text-to-motion and music-to-dance. Previous …

We introduce DiffH2O, a new diffusion-based framework for synthesizing realistic, dexterous
hand-object interactions from natural language. Our model employs a temporal two-stage …

In this study, we tackle the complex task of generating 3D human-object interactions (HOI)
from textual descriptions in a zero-shot text-to-3D manner. We identify and address two key …

Existing 3D human object interaction (HOI) datasets and models simply align global
descriptions with the long HOI sequence, while lacking a detailed understanding of …

Perceiving 3D structures from RGB images based on CAD model primitives can enable an
effective, efficient 3D object-based representation of scenes. However, current approaches …

Understanding how humans cooperatively rearrange household objects is critical for VR/AR
and human-robot interaction. However, in-depth studies on modeling these behaviors are …

Crowd Motion Generation is essential in entertainment industries such as animation and
games as well as in strategic fields like urban simulation and planning. This new task …

This paper addresses new methodologies to deal with the challenging task of generating
dynamic Human-Object Interactions from textual descriptions (Text2HOI). While most …

Learning generic skills for humanoid robots interacting with 3D scenes by mimicking human
data is a key research challenge with significant implications for robotics and real-world …