Saved in:
Bibliographic Details
Main Authors: Gao, Xuehao, Yang, Yang, Du, Shaoyi, Wu, Yang, Liu, Yebin, Qi, Guo-Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.00382
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909523687505920
author Gao, Xuehao
Yang, Yang
Du, Shaoyi
Wu, Yang
Liu, Yebin
Qi, Guo-Jun
author_facet Gao, Xuehao
Yang, Yang
Du, Shaoyi
Wu, Yang
Liu, Yebin
Qi, Guo-Jun
contents This paper explores a cross-modality synthesis task that infers 3D human-object interactions (HOIs) from a given text-based instruction. Existing text-to-HOI synthesis methods mainly deploy a direct mapping from texts to object-specific 3D body motions, which may encounter a performance bottleneck since the huge cross-modality gap. In this paper, we observe that those HOI samples with the same interaction intention toward different targets, e.g., "lift a chair" and "lift a cup", always encapsulate similar action-specific body motion patterns while characterizing different object-specific interaction styles. Thus, learning effective action-specific motion priors and object-specific interaction priors is crucial for a text-to-HOI model and dominates its performances on text-HOI semantic consistency and body-object interaction realism. In light of this, we propose a novel body pose generation strategy for the text-to-HOI task: infer object-agnostic canonical body action first and then enrich object-specific interaction styles. Specifically, the first canonical body action inference stage focuses on learning intra-class shareable body motion priors and mapping given text-based semantics to action-specific canonical 3D body motions. Then, in the object-specific interaction inference stage, we focus on object affordance learning and enrich object-specific interaction styles on an inferred action-specific body motion basis. Extensive experiments verify that our proposed text-to-HOI synthesis system significantly outperforms other SOTA methods on three large-scale datasets with better semantic consistency and interaction realism performances.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00382
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning
Gao, Xuehao
Yang, Yang
Du, Shaoyi
Wu, Yang
Liu, Yebin
Qi, Guo-Jun
Computer Vision and Pattern Recognition
This paper explores a cross-modality synthesis task that infers 3D human-object interactions (HOIs) from a given text-based instruction. Existing text-to-HOI synthesis methods mainly deploy a direct mapping from texts to object-specific 3D body motions, which may encounter a performance bottleneck since the huge cross-modality gap. In this paper, we observe that those HOI samples with the same interaction intention toward different targets, e.g., "lift a chair" and "lift a cup", always encapsulate similar action-specific body motion patterns while characterizing different object-specific interaction styles. Thus, learning effective action-specific motion priors and object-specific interaction priors is crucial for a text-to-HOI model and dominates its performances on text-HOI semantic consistency and body-object interaction realism. In light of this, we propose a novel body pose generation strategy for the text-to-HOI task: infer object-agnostic canonical body action first and then enrich object-specific interaction styles. Specifically, the first canonical body action inference stage focuses on learning intra-class shareable body motion priors and mapping given text-based semantics to action-specific canonical 3D body motions. Then, in the object-specific interaction inference stage, we focus on object affordance learning and enrich object-specific interaction styles on an inferred action-specific body motion basis. Extensive experiments verify that our proposed text-to-HOI synthesis system significantly outperforms other SOTA methods on three large-scale datasets with better semantic consistency and interaction realism performances.
title EigenActor: Variant Body-Object Interaction Generation Evolved from Invariant Action Basis Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.00382