Dex2HOI: Dexterous Bimanual Two-Object Interaction Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pratikaki, Chrysa, Ruiz-Ponce, Pablo, Deng, Jiankang, Zafeiriou, Stefanos, Potamias, Rolandos Alexandros
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910270717165568
author Pratikaki, Chrysa
Ruiz-Ponce, Pablo
Deng, Jiankang
Zafeiriou, Stefanos
Potamias, Rolandos Alexandros
author_facet Pratikaki, Chrysa
Ruiz-Ponce, Pablo
Deng, Jiankang
Zafeiriou, Stefanos
Potamias, Rolandos Alexandros
contents Recent advances in 4D Human-Object Interaction (HOI) generation have enabled increasingly realistic motion synthesis, particularly for single-object manipulation. Yet current research overlooks an inherent property of human behavior: people naturally coordinate both hands and manipulate multiple objects simultaneously. To address this gap, we present Dex2HOI, a unified diffusion model for single- and two-object HOI synthesis from text. At its core, Dex2HOI employs a Dual-Stream Diffusion approach, where each object is processed in a dedicated interaction stream and coordinated through bidirectional cross-attention. To synthesize the final motion, we introduce a Motion Fusion Network integrated with novel hand-relative object representations and contact-aware conditioning applied across the whole sequence. By sampling the diffusion process autoregressively over prefix-conditioned windows, Dex2HOI generates arbitrarily long sequences at real-time speed omitting redundant test-time optimization, achieving up to x540 inference speed-up over prior state-of-the-art methods. Extensive evaluation on both single- and two-object benchmarks demonstrates state-of-the-art quantitative results, marking a step beyond conventional single-object HOI generation and toward expressive multi-object manipulation. Code and models will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30444
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Dex2HOI: Dexterous Bimanual Two-Object Interaction Generation
Pratikaki, Chrysa
Ruiz-Ponce, Pablo
Deng, Jiankang
Zafeiriou, Stefanos
Potamias, Rolandos Alexandros
Computer Vision and Pattern Recognition
Recent advances in 4D Human-Object Interaction (HOI) generation have enabled increasingly realistic motion synthesis, particularly for single-object manipulation. Yet current research overlooks an inherent property of human behavior: people naturally coordinate both hands and manipulate multiple objects simultaneously. To address this gap, we present Dex2HOI, a unified diffusion model for single- and two-object HOI synthesis from text. At its core, Dex2HOI employs a Dual-Stream Diffusion approach, where each object is processed in a dedicated interaction stream and coordinated through bidirectional cross-attention. To synthesize the final motion, we introduce a Motion Fusion Network integrated with novel hand-relative object representations and contact-aware conditioning applied across the whole sequence. By sampling the diffusion process autoregressively over prefix-conditioned windows, Dex2HOI generates arbitrarily long sequences at real-time speed omitting redundant test-time optimization, achieving up to x540 inference speed-up over prior state-of-the-art methods. Extensive evaluation on both single- and two-object benchmarks demonstrates state-of-the-art quantitative results, marking a step beyond conventional single-object HOI generation and toward expressive multi-object manipulation. Code and models will be released upon acceptance.
title Dex2HOI: Dexterous Bimanual Two-Object Interaction Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.30444