SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Wenjia, Pan, Liang, Dou, Zhiyang, Mei, Jidong, Liao, Zhouyingcheng, Lou, Yuke, Wu, Yifan, Yang, Lei, Wang, Jingbo, Komura, Taku
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929761058553856
author Wang, Wenjia
Pan, Liang
Dou, Zhiyang
Mei, Jidong
Liao, Zhouyingcheng
Lou, Yuke
Wu, Yifan
Yang, Lei
Wang, Jingbo
Komura, Taku
author_facet Wang, Wenjia
Pan, Liang
Dou, Zhiyang
Mei, Jidong
Liao, Zhouyingcheng
Lou, Yuke
Wu, Yifan
Yang, Lei
Wang, Jingbo
Komura, Taku
contents Simulating stylized human-scene interactions (HSI) in physical environments is a challenging yet fascinating task. Prior works emphasize long-term execution but fall short in achieving both diverse style and physical plausibility. To tackle this challenge, we introduce a novel hierarchical framework named SIMS that seamlessly bridges highlevel script-driven intent with a low-level control policy, enabling more expressive and diverse human-scene interactions. Specifically, we employ Large Language Models with Retrieval-Augmented Generation (RAG) to generate coherent and diverse long-form scripts, providing a rich foundation for motion planning. A versatile multicondition physics-based control policy is also developed, which leverages text embeddings from the generated scripts to encode stylistic cues, simultaneously perceiving environmental geometries and accomplishing task goals. By integrating the retrieval-augmented script generation with the multi-condition controller, our approach provides a unified solution for generating stylized HSI motions. We further introduce a comprehensive planning dataset produced by RAG and a stylized motion dataset featuring diverse locomotions and interactions. Extensive experiments demonstrate SIMS's effectiveness in executing various tasks and generalizing across different scenarios, significantly outperforming previous methods.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19921
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation
Wang, Wenjia
Pan, Liang
Dou, Zhiyang
Mei, Jidong
Liao, Zhouyingcheng
Lou, Yuke
Wu, Yifan
Yang, Lei
Wang, Jingbo
Komura, Taku
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Graphics
Simulating stylized human-scene interactions (HSI) in physical environments is a challenging yet fascinating task. Prior works emphasize long-term execution but fall short in achieving both diverse style and physical plausibility. To tackle this challenge, we introduce a novel hierarchical framework named SIMS that seamlessly bridges highlevel script-driven intent with a low-level control policy, enabling more expressive and diverse human-scene interactions. Specifically, we employ Large Language Models with Retrieval-Augmented Generation (RAG) to generate coherent and diverse long-form scripts, providing a rich foundation for motion planning. A versatile multicondition physics-based control policy is also developed, which leverages text embeddings from the generated scripts to encode stylistic cues, simultaneously perceiving environmental geometries and accomplishing task goals. By integrating the retrieval-augmented script generation with the multi-condition controller, our approach provides a unified solution for generating stylized HSI motions. We further introduce a comprehensive planning dataset produced by RAG and a stylized motion dataset featuring diverse locomotions and interactions. Extensive experiments demonstrate SIMS's effectiveness in executing various tasks and generalizing across different scenarios, significantly outperforming previous methods.
title SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Graphics
url https://arxiv.org/abs/2411.19921