HORT: Monocular Hand-held Objects Reconstruction with Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zerui, Potamias, Rolandos Alexandros, Chen, Shizhe, Schmid, Cordelia
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916853490647040
author Chen, Zerui
Potamias, Rolandos Alexandros
Chen, Shizhe
Schmid, Cordelia
author_facet Chen, Zerui
Potamias, Rolandos Alexandros
Chen, Shizhe
Schmid, Cordelia
contents Reconstructing hand-held objects in 3D from monocular images remains a significant challenge in computer vision. Most existing approaches rely on implicit 3D representations, which produce overly smooth reconstructions and are time-consuming to generate explicit 3D shapes. While more recent methods directly reconstruct point clouds with diffusion models, the multi-step denoising makes high-resolution reconstruction inefficient. To address these limitations, we propose a transformer-based model to efficiently reconstruct dense 3D point clouds of hand-held objects. Our method follows a coarse-to-fine strategy, first generating a sparse point cloud from the image and progressively refining it into a dense representation using pixel-aligned image features. To enhance reconstruction accuracy, we integrate image features with 3D hand geometry to jointly predict the object point cloud and its pose relative to the hand. Our model is trained end-to-end for optimal performance. Experimental results on both synthetic and real datasets demonstrate that our method achieves state-of-the-art accuracy with much faster inference speed, while generalizing well to in-the-wild images.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21313
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HORT: Monocular Hand-held Objects Reconstruction with Transformers
Chen, Zerui
Potamias, Rolandos Alexandros
Chen, Shizhe
Schmid, Cordelia
Computer Vision and Pattern Recognition
Reconstructing hand-held objects in 3D from monocular images remains a significant challenge in computer vision. Most existing approaches rely on implicit 3D representations, which produce overly smooth reconstructions and are time-consuming to generate explicit 3D shapes. While more recent methods directly reconstruct point clouds with diffusion models, the multi-step denoising makes high-resolution reconstruction inefficient. To address these limitations, we propose a transformer-based model to efficiently reconstruct dense 3D point clouds of hand-held objects. Our method follows a coarse-to-fine strategy, first generating a sparse point cloud from the image and progressively refining it into a dense representation using pixel-aligned image features. To enhance reconstruction accuracy, we integrate image features with 3D hand geometry to jointly predict the object point cloud and its pose relative to the hand. Our model is trained end-to-end for optimal performance. Experimental results on both synthetic and real datasets demonstrate that our method achieves state-of-the-art accuracy with much faster inference speed, while generalizing well to in-the-wild images.
title HORT: Monocular Hand-held Objects Reconstruction with Transformers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.21313