VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Mao, Aihua, Huang, Kaihang, Liu, Yong-Jin, Chan, Chee Seng, He, Ying
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911464513601536
author Mao, Aihua
Huang, Kaihang
Liu, Yong-Jin
Chan, Chee Seng
He, Ying
author_facet Mao, Aihua
Huang, Kaihang
Liu, Yong-Jin
Chan, Chee Seng
He, Ying
contents 3D object affordance grounding aims to identify regions on 3D objects that support human-object interaction (HOI), a capability essential to embodied visual reasoning. However, most existing approaches rely on static visual or textual cues, neglecting that affordances are inherently defined by dynamic actions. As a result, they often struggle to localize the true contact regions involved in real interactions. We take a different perspective. Humans learn how to use objects by observing and imitating actions, not just by examining shapes. Motivated by this intuition, we introduce video-guided 3D affordance grounding, which leverages dynamic interaction sequences to provide functional supervision. To achieve this, we propose VAGNet, a framework that aligns video-derived interaction cues with 3D structure to resolve ambiguities that static cues cannot address. To support this new setting, we introduce PVAD, the first HOI video-3D pairing affordance dataset, providing functional supervision unavailable in prior works. Extensive experiments on PVAD show that VAGNet achieves state-of-the-art performance, significantly outperforming static-based baselines. The code and dataset will be open publicly.
format Preprint
id arxiv_https___arxiv_org_abs_2602_20608
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos
Mao, Aihua
Huang, Kaihang
Liu, Yong-Jin
Chan, Chee Seng
He, Ying
Computer Vision and Pattern Recognition
3D object affordance grounding aims to identify regions on 3D objects that support human-object interaction (HOI), a capability essential to embodied visual reasoning. However, most existing approaches rely on static visual or textual cues, neglecting that affordances are inherently defined by dynamic actions. As a result, they often struggle to localize the true contact regions involved in real interactions. We take a different perspective. Humans learn how to use objects by observing and imitating actions, not just by examining shapes. Motivated by this intuition, we introduce video-guided 3D affordance grounding, which leverages dynamic interaction sequences to provide functional supervision. To achieve this, we propose VAGNet, a framework that aligns video-derived interaction cues with 3D structure to resolve ambiguities that static cues cannot address. To support this new setting, we introduce PVAD, the first HOI video-3D pairing affordance dataset, providing functional supervision unavailable in prior works. Extensive experiments on PVAD show that VAGNet achieves state-of-the-art performance, significantly outperforming static-based baselines. The code and dataset will be open publicly.
title VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.20608