Saved in:
Bibliographic Details
Main Authors: Wang, Jiepeng, Pan, Hao, Liu, Yang, Tong, Xin, Komura, Taku, Wang, Wenping
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.17510
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909581924368384
author Wang, Jiepeng
Pan, Hao
Liu, Yang
Tong, Xin
Komura, Taku
Wang, Wenping
author_facet Wang, Jiepeng
Pan, Hao
Liu, Yang
Tong, Xin
Komura, Taku
Wang, Wenping
contents Man-made 3D shapes are naturally organized in parts and hierarchies; such structures provide important constraints for shape reconstruction and generation. Modeling shape structures is difficult, because there can be multiple hierarchies for a given shape, causing ambiguity, and across different categories the shape structures are correlated with semantics, limiting generalization. We present StructRe, a structure rewriting system, as a novel approach to structured shape modeling. Given a 3D object represented by points and components, StructRe can rewrite it upward into more concise structures, or downward into more detailed structures; by iterating the rewriting process, hierarchies are obtained. Such a localized rewriting process enables probabilistic modeling of ambiguous structures and robust generalization across object categories. We train StructRe on PartNet data and show its generalization to cross-category and multiple object hierarchies, and test its extension to ShapeNet. We also demonstrate the benefits of probabilistic and generalizable structure modeling for shape reconstruction, generation and editing tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2311_17510
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle StructRe: Rewriting for Structured Shape Modeling
Wang, Jiepeng
Pan, Hao
Liu, Yang
Tong, Xin
Komura, Taku
Wang, Wenping
Computer Vision and Pattern Recognition
Man-made 3D shapes are naturally organized in parts and hierarchies; such structures provide important constraints for shape reconstruction and generation. Modeling shape structures is difficult, because there can be multiple hierarchies for a given shape, causing ambiguity, and across different categories the shape structures are correlated with semantics, limiting generalization. We present StructRe, a structure rewriting system, as a novel approach to structured shape modeling. Given a 3D object represented by points and components, StructRe can rewrite it upward into more concise structures, or downward into more detailed structures; by iterating the rewriting process, hierarchies are obtained. Such a localized rewriting process enables probabilistic modeling of ambiguous structures and robust generalization across object categories. We train StructRe on PartNet data and show its generalization to cross-category and multiple object hierarchies, and test its extension to ShapeNet. We also demonstrate the benefits of probabilistic and generalizable structure modeling for shape reconstruction, generation and editing tasks.
title StructRe: Rewriting for Structured Shape Modeling
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.17510