HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zerui, Potamias, Rolandos Alexandros, Chen, Shizhe, Deng, Jiankang, Schmid, Cordelia, Zafeiriou, Stefanos
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914467388850176
author Chen, Zerui
Potamias, Rolandos Alexandros
Chen, Shizhe
Deng, Jiankang
Schmid, Cordelia
Zafeiriou, Stefanos
author_facet Chen, Zerui
Potamias, Rolandos Alexandros
Chen, Shizhe
Deng, Jiankang
Schmid, Cordelia
Zafeiriou, Stefanos
contents Generating realistic 3D hand-object interactions (HOI) is a fundamental challenge in computer vision and robotics, requiring both temporal coherence and high-fidelity physical plausibility. Existing methods remain limited in their ability to learn expressive motion representations for generation and perform temporal reasoning. In this paper, we present HO-Flow, a framework for synthesizing realistic hand-object motion sequences from texts and canoncial 3D objects. HO-Flow first employs an interaction-aware variational autoencoder to encode sequences of hand and object motions into a unified latent manifold by incorporating hand and object kinematics, enabling the representation to capture rich interaction dynamics. It then leverages a masked flow matching model that combines auto-regressive temporal reasoning with continuous latent generation, improving temporal coherence. To further enhance generalization, HO-Flow predicts object motions relative to the initial frame, enabling effective pre-training on large-scale synthetic data. Experiments on the GRAB, OakInk, and DexYCB benchmarks demonstrate that HO-Flow achieves state-of-the-art performance in both physical plausibility and motion diversity for interaction motion synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10836
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching
Chen, Zerui
Potamias, Rolandos Alexandros
Chen, Shizhe
Deng, Jiankang
Schmid, Cordelia
Zafeiriou, Stefanos
Computer Vision and Pattern Recognition
Robotics
Generating realistic 3D hand-object interactions (HOI) is a fundamental challenge in computer vision and robotics, requiring both temporal coherence and high-fidelity physical plausibility. Existing methods remain limited in their ability to learn expressive motion representations for generation and perform temporal reasoning. In this paper, we present HO-Flow, a framework for synthesizing realistic hand-object motion sequences from texts and canoncial 3D objects. HO-Flow first employs an interaction-aware variational autoencoder to encode sequences of hand and object motions into a unified latent manifold by incorporating hand and object kinematics, enabling the representation to capture rich interaction dynamics. It then leverages a masked flow matching model that combines auto-regressive temporal reasoning with continuous latent generation, improving temporal coherence. To further enhance generalization, HO-Flow predicts object motions relative to the initial frame, enabling effective pre-training on large-scale synthetic data. Experiments on the GRAB, OakInk, and DexYCB benchmarks demonstrate that HO-Flow achieves state-of-the-art performance in both physical plausibility and motion diversity for interaction motion synthesis.
title HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2604.10836