HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Swamy, Anilkumar, Leroy, Vincent, Weinzaepfel, Philippe, Franco, Jean-Sébastien, Rogez, Grégory
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912552775057408
author Swamy, Anilkumar
Leroy, Vincent
Weinzaepfel, Philippe
Franco, Jean-Sébastien
Rogez, Grégory
author_facet Swamy, Anilkumar
Leroy, Vincent
Weinzaepfel, Philippe
Franco, Jean-Sébastien
Rogez, Grégory
contents Hand-object 3D reconstruction has become increasingly important for applications in human-robot interaction and immersive AR/VR experiences. A common approach for object-agnostic hand-object reconstruction from RGB sequences involves a two-stage pipeline: hand-object 3D tracking followed by multi-view 3D reconstruction. However, existing methods rely on keypoint detection techniques, such as Structure from Motion (SfM) and hand-keypoint optimization, which struggle with diverse object geometries, weak textures, and mutual hand-object occlusions, limiting scalability and generalization. As a key enabler to generic and seamless, non-intrusive applicability, we propose in this work a robust, keypoint detector-free approach to estimating hand-object 3D transformations from monocular motion video/images. We further integrate this with a multi-view reconstruction pipeline to accurately recover hand-object 3D shape. Our method, named HOSt3R, is unconstrained, does not rely on pre-scanned object templates or camera intrinsics, and reaches state-of-the-art performance for the tasks of object-agnostic hand-object 3D transformation and shape estimation on the SHOWMe benchmark. We also experiment on sequences from the HO3D dataset, demonstrating generalization to unseen object categories.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16465
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images
Swamy, Anilkumar
Leroy, Vincent
Weinzaepfel, Philippe
Franco, Jean-Sébastien
Rogez, Grégory
Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Robotics
Hand-object 3D reconstruction has become increasingly important for applications in human-robot interaction and immersive AR/VR experiences. A common approach for object-agnostic hand-object reconstruction from RGB sequences involves a two-stage pipeline: hand-object 3D tracking followed by multi-view 3D reconstruction. However, existing methods rely on keypoint detection techniques, such as Structure from Motion (SfM) and hand-keypoint optimization, which struggle with diverse object geometries, weak textures, and mutual hand-object occlusions, limiting scalability and generalization. As a key enabler to generic and seamless, non-intrusive applicability, we propose in this work a robust, keypoint detector-free approach to estimating hand-object 3D transformations from monocular motion video/images. We further integrate this with a multi-view reconstruction pipeline to accurately recover hand-object 3D shape. Our method, named HOSt3R, is unconstrained, does not rely on pre-scanned object templates or camera intrinsics, and reaches state-of-the-art performance for the tasks of object-agnostic hand-object 3D transformation and shape estimation on the SHOWMe benchmark. We also experiment on sequences from the HO3D dataset, demonstrating generalization to unseen object categories.
title HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Robotics
url https://arxiv.org/abs/2508.16465