Unified Human-Scene Interaction via Prompted Chain-of-Contacts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Zeqi, Wang, Tai, Wang, Jingbo, Cao, Jinkun, Zhang, Wenwei, Dai, Bo, Lin, Dahua, Pang, Jiangmiao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908119322329088
author Xiao, Zeqi
Wang, Tai
Wang, Jingbo
Cao, Jinkun
Zhang, Wenwei
Dai, Bo
Lin, Dahua
Pang, Jiangmiao
author_facet Xiao, Zeqi
Wang, Tai
Wang, Jingbo
Cao, Jinkun
Zhang, Wenwei
Dai, Bo
Lin, Dahua
Pang, Jiangmiao
contents Human-Scene Interaction (HSI) is a vital component of fields like embodied AI and virtual reality. Despite advancements in motion quality and physical plausibility, two pivotal factors, versatile interaction control and the development of a user-friendly interface, require further exploration before the practical application of HSI. This paper presents a unified HSI framework, UniHSI, which supports unified control of diverse interactions through language commands. This framework is built upon the definition of interaction as Chain of Contacts (CoC): steps of human joint-object part pairs, which is inspired by the strong correlation between interaction types and human-object contact regions. Based on the definition, UniHSI constitutes a Large Language Model (LLM) Planner to translate language prompts into task plans in the form of CoC, and a Unified Controller that turns CoC into uniform task execution. To facilitate training and evaluation, we collect a new dataset named ScenePlan that encompasses thousands of task plans generated by LLMs based on diverse scenarios. Comprehensive experiments demonstrate the effectiveness of our framework in versatile task execution and generalizability to real scanned scenes. The project page is at https://github.com/OpenRobotLab/UniHSI .
format Preprint
id arxiv_https___arxiv_org_abs_2309_07918
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Unified Human-Scene Interaction via Prompted Chain-of-Contacts
Xiao, Zeqi
Wang, Tai
Wang, Jingbo
Cao, Jinkun
Zhang, Wenwei
Dai, Bo
Lin, Dahua
Pang, Jiangmiao
Computer Vision and Pattern Recognition
Human-Scene Interaction (HSI) is a vital component of fields like embodied AI and virtual reality. Despite advancements in motion quality and physical plausibility, two pivotal factors, versatile interaction control and the development of a user-friendly interface, require further exploration before the practical application of HSI. This paper presents a unified HSI framework, UniHSI, which supports unified control of diverse interactions through language commands. This framework is built upon the definition of interaction as Chain of Contacts (CoC): steps of human joint-object part pairs, which is inspired by the strong correlation between interaction types and human-object contact regions. Based on the definition, UniHSI constitutes a Large Language Model (LLM) Planner to translate language prompts into task plans in the form of CoC, and a Unified Controller that turns CoC into uniform task execution. To facilitate training and evaluation, we collect a new dataset named ScenePlan that encompasses thousands of task plans generated by LLMs based on diverse scenarios. Comprehensive experiments demonstrate the effectiveness of our framework in versatile task execution and generalizability to real scanned scenes. The project page is at https://github.com/OpenRobotLab/UniHSI .
title Unified Human-Scene Interaction via Prompted Chain-of-Contacts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.07918