ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Hongjie, Yu, Hong-Xing, Li, Jiaman, Wu, Jiajun
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909546796023808
author Li, Hongjie
Yu, Hong-Xing
Li, Jiaman
Wu, Jiajun
author_facet Li, Hongjie
Yu, Hong-Xing
Li, Jiaman
Wu, Jiajun
contents Human-scene interaction (HSI) generation is crucial for applications in embodied AI, virtual reality, and robotics. Yet, existing methods cannot synthesize interactions in unseen environments such as in-the-wild scenes or reconstructed scenes, as they rely on paired 3D scenes and captured human motion data for training, which are unavailable for unseen environments. We present ZeroHSI, a novel approach that enables zero-shot 4D human-scene interaction synthesis, eliminating the need for training on any MoCap data. Our key insight is to distill human-scene interactions from state-of-the-art video generation models, which have been trained on vast amounts of natural human movements and interactions, and use differentiable rendering to reconstruct human-scene interactions. ZeroHSI can synthesize realistic human motions in both static scenes and environments with dynamic objects, without requiring any ground-truth motion data. We evaluate ZeroHSI on a curated dataset of different types of various indoor and outdoor scenes with different interaction prompts, demonstrating its ability to generate diverse and contextually appropriate human-scene interactions.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18600
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation
Li, Hongjie
Yu, Hong-Xing
Li, Jiaman
Wu, Jiajun
Computer Vision and Pattern Recognition
Graphics
Human-scene interaction (HSI) generation is crucial for applications in embodied AI, virtual reality, and robotics. Yet, existing methods cannot synthesize interactions in unseen environments such as in-the-wild scenes or reconstructed scenes, as they rely on paired 3D scenes and captured human motion data for training, which are unavailable for unseen environments. We present ZeroHSI, a novel approach that enables zero-shot 4D human-scene interaction synthesis, eliminating the need for training on any MoCap data. Our key insight is to distill human-scene interactions from state-of-the-art video generation models, which have been trained on vast amounts of natural human movements and interactions, and use differentiable rendering to reconstruct human-scene interactions. ZeroHSI can synthesize realistic human motions in both static scenes and environments with dynamic objects, without requiring any ground-truth motion data. We evaluate ZeroHSI on a curated dataset of different types of various indoor and outdoor scenes with different interaction prompts, demonstrating its ability to generate diverse and contextually appropriate human-scene interactions.
title ZeroHSI: Zero-Shot 4D Human-Scene Interaction by Video Generation
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2412.18600