We address the problem of generating realistic 3D motions of humans interacting with
objects in a scene. Our key idea is to create a neural interaction field attached to a specific …

Generating realistic 3D worlds occupied by moving humans has many applications in
games, architecture, and synthetic data creation. But generating such scenes is expensive …

We tackle the task of reconstructing hand-object interactions from short video clips. Given an
input video, our approach casts 3D inference as a per-video optimization and recovers a …

We present TeSMo, a text-controlled scene-aware motion generation method based on
denoising diffusion models. Previous text-to-motion methods focus on characters in isolation …

Learning 3D human-object interaction relation is pivotal to embodied AI and interaction
modeling. Most existing methods approach the goal by learning to predict isolated …

Existing automatic approaches for 3D virtual character motion synthesis supporting scene
interactions do not gen-eralise well to new objects outside training distributions, even when …

Scene synthesis is a challenging problem with several industrial applications. Recently,
substantial efforts have been directed to synthesize the scene using human motions, room …

We present an approach to generate virtual activity snippets, which comprise sequenced
keyframes of multi-character, multi-object interaction scenarios in 3D environments, by …

Human-scene Interaction (HSI) generation is a challenging task and crucial for various
downstream tasks. However, one of the major obstacles is its limited data scale. High-quality …

3D scene synthesis facilitates and benefits many real-world applications. Most scene
generators focus on making indoor scenes plausible via learning from training data and …