Saved in:
Bibliographic Details
Main Authors: Reka, Melvin, Pulli, Tessa, Vincze, Markus
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.07190
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913727884820480
author Reka, Melvin
Pulli, Tessa
Vincze, Markus
author_facet Reka, Melvin
Pulli, Tessa
Vincze, Markus
contents 6D object pose estimation for unseen objects is essential in robotics but traditionally relies on trained models that require large datasets, high computational costs, and struggle to generalize. Zero-shot approaches eliminate the need for training but depend on pre-existing 3D object models, which are often impractical to obtain. To address this, we propose a language-guided few-shot 3D reconstruction method, reconstructing a 3D mesh from few input images. In the proposed pipeline, receives a set of input images and a language query. A combination of GroundingDINO and Segment Anything Model outputs segmented masks from which a sparse point cloud is reconstructed with VGGSfM. Subsequently, the mesh is reconstructed with the Gaussian Splatting method SuGAR. In a final cleaning step, artifacts are removed, resulting in the final 3D mesh of the queried object. We evaluate the method in terms of accuracy and quality of the geometry and texture. Furthermore, we study the impact of imaging conditions such as viewing angle, number of input images, and image overlap on 3D object reconstruction quality, efficiency, and computational scalability.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07190
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Modal 3D Mesh Reconstruction from Images and Text
Reka, Melvin
Pulli, Tessa
Vincze, Markus
Computer Vision and Pattern Recognition
Computation and Language
6D object pose estimation for unseen objects is essential in robotics but traditionally relies on trained models that require large datasets, high computational costs, and struggle to generalize. Zero-shot approaches eliminate the need for training but depend on pre-existing 3D object models, which are often impractical to obtain. To address this, we propose a language-guided few-shot 3D reconstruction method, reconstructing a 3D mesh from few input images. In the proposed pipeline, receives a set of input images and a language query. A combination of GroundingDINO and Segment Anything Model outputs segmented masks from which a sparse point cloud is reconstructed with VGGSfM. Subsequently, the mesh is reconstructed with the Gaussian Splatting method SuGAR. In a final cleaning step, artifacts are removed, resulting in the final 3D mesh of the queried object. We evaluate the method in terms of accuracy and quality of the geometry and texture. Furthermore, we study the impact of imaging conditions such as viewing angle, number of input images, and image overlap on 3D object reconstruction quality, efficiency, and computational scalability.
title Multi-Modal 3D Mesh Reconstruction from Images and Text
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2503.07190