Saved in:
Bibliographic Details
Main Authors: Zhang, Ruiyuan, Liu, Jiaxiang, Li, Zexi, Dong, Hao, Fu, Jie, Wu, Chao
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.12340
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917567075975168
author Zhang, Ruiyuan
Liu, Jiaxiang
Li, Zexi
Dong, Hao
Fu, Jie
Wu, Chao
author_facet Zhang, Ruiyuan
Liu, Jiaxiang
Li, Zexi
Dong, Hao
Fu, Jie
Wu, Chao
contents Geometric fracture assembly presents a challenging practical task in archaeology and 3D computer vision. Previous methods have focused solely on assembling fragments based on semantic information, which has limited the quantity of objects that can be effectively assembled. Therefore, there is a need to develop a scalable framework for geometric fracture assembly without relying on semantic information. To improve the effectiveness of assembling geometric fractures without semantic information, we propose a co-creation space comprising several assemblers capable of gradually and unambiguously assembling fractures. Additionally, we introduce a novel loss function, i.e., the geometric-based collision loss, to address collision issues during the fracture assembly process and enhance the results. Our framework exhibits better performance on both PartNet and Breaking Bad datasets compared to existing state-of-the-art frameworks. Extensive experiments and quantitative comparisons demonstrate the effectiveness of our proposed framework, which features linear computational complexity, enhanced abstraction, and improved generalization. Our code is publicly available at https://github.com/Ruiyuan-Zhang/CCS.
format Preprint
id arxiv_https___arxiv_org_abs_2312_12340
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers
Zhang, Ruiyuan
Liu, Jiaxiang
Li, Zexi
Dong, Hao
Fu, Jie
Wu, Chao
Computer Vision and Pattern Recognition
Geometric fracture assembly presents a challenging practical task in archaeology and 3D computer vision. Previous methods have focused solely on assembling fragments based on semantic information, which has limited the quantity of objects that can be effectively assembled. Therefore, there is a need to develop a scalable framework for geometric fracture assembly without relying on semantic information. To improve the effectiveness of assembling geometric fractures without semantic information, we propose a co-creation space comprising several assemblers capable of gradually and unambiguously assembling fractures. Additionally, we introduce a novel loss function, i.e., the geometric-based collision loss, to address collision issues during the fracture assembly process and enhance the results. Our framework exhibits better performance on both PartNet and Breaking Bad datasets compared to existing state-of-the-art frameworks. Extensive experiments and quantitative comparisons demonstrate the effectiveness of our proposed framework, which features linear computational complexity, enhanced abstraction, and improved generalization. Our code is publicly available at https://github.com/Ruiyuan-Zhang/CCS.
title Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.12340