G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Cheng, Junfeng, Stathaki, Tania
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911873238040576
author Cheng, Junfeng
Stathaki, Tania
author_facet Cheng, Junfeng
Stathaki, Tania
contents This paper proposes a novel task named "3D part grouping". Suppose there is a mixed set containing scattered parts from various shapes. This task requires algorithms to find out every possible combination among all the parts. To address this challenge, we propose the so called Gradient Field-based Auto-Regressive Sampling framework (G-FARS) tailored specifically for the 3D part grouping task. In our framework, we design a gradient-field-based selection graph neural network (GNN) to learn the gradients of a log conditional probability density in terms of part selection, where the condition is the given mixed part set. This innovative approach, implemented through the gradient-field-based selection GNN, effectively captures complex relationships among all the parts in the input. Upon completion of the training process, our framework becomes capable of autonomously grouping 3D parts by iteratively selecting them from the mixed part set, leveraging the knowledge acquired by the trained gradient-field-based selection GNN. Our code is available at: https://github.com/J-F-Cheng/G-FARS-3DPartGrouping.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06828
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping
Cheng, Junfeng
Stathaki, Tania
Computer Vision and Pattern Recognition
This paper proposes a novel task named "3D part grouping". Suppose there is a mixed set containing scattered parts from various shapes. This task requires algorithms to find out every possible combination among all the parts. To address this challenge, we propose the so called Gradient Field-based Auto-Regressive Sampling framework (G-FARS) tailored specifically for the 3D part grouping task. In our framework, we design a gradient-field-based selection graph neural network (GNN) to learn the gradients of a log conditional probability density in terms of part selection, where the condition is the given mixed part set. This innovative approach, implemented through the gradient-field-based selection GNN, effectively captures complex relationships among all the parts in the input. Upon completion of the training process, our framework becomes capable of autonomously grouping 3D parts by iteratively selecting them from the mixed part set, leveraging the knowledge acquired by the trained gradient-field-based selection GNN. Our code is available at: https://github.com/J-F-Cheng/G-FARS-3DPartGrouping.
title G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.06828