Generate Point Clouds with Multiscale Details from Graph-Represented Structures

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Ximing, Zhang, Zhibo, He, Zhengfu, Jin, Cheng
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929335678533632
author Yang, Ximing
Zhang, Zhibo
He, Zhengfu
Jin, Cheng
author_facet Yang, Ximing
Zhang, Zhibo
He, Zhengfu
Jin, Cheng
contents As details are missing in most representations of structures, the lack of controllability to more information is one of the major weaknesses in structure-based controllable point cloud generation. It is observable that definitions of details and structures are subjective. Details can be treated as structures on small scales. To represent structures in different scales at the same time, we present a graph-based representation of structures called the Multiscale Structure Graph (MSG). Given structures in multiple scales, similar patterns of local structures can be found at different scales, positions, and angles. The knowledge learned from a regional structure pattern shall be transferred to other similar patterns. An encoding and generation mechanism, namely the Multiscale Structure-based Point Cloud Generator (MSPCG) is proposed, which can simultaneously learn point cloud generation from local patterns with miscellaneous spatial properties. The proposed method supports multiscale editions on point clouds by editing the MSG. By generating point clouds from local structures and learning simultaneously in multiple scales, our MSPCG has better generalization ability and scalability. Trained on the ShapeNet, our MSPCG can generate point clouds from a given structure for unseen categories and indoor scenes. The experimental results show that our method significantly outperforms baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2112_06433
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Generate Point Clouds with Multiscale Details from Graph-Represented Structures
Yang, Ximing
Zhang, Zhibo
He, Zhengfu
Jin, Cheng
Computer Vision and Pattern Recognition
Artificial Intelligence
As details are missing in most representations of structures, the lack of controllability to more information is one of the major weaknesses in structure-based controllable point cloud generation. It is observable that definitions of details and structures are subjective. Details can be treated as structures on small scales. To represent structures in different scales at the same time, we present a graph-based representation of structures called the Multiscale Structure Graph (MSG). Given structures in multiple scales, similar patterns of local structures can be found at different scales, positions, and angles. The knowledge learned from a regional structure pattern shall be transferred to other similar patterns. An encoding and generation mechanism, namely the Multiscale Structure-based Point Cloud Generator (MSPCG) is proposed, which can simultaneously learn point cloud generation from local patterns with miscellaneous spatial properties. The proposed method supports multiscale editions on point clouds by editing the MSG. By generating point clouds from local structures and learning simultaneously in multiple scales, our MSPCG has better generalization ability and scalability. Trained on the ShapeNet, our MSPCG can generate point clouds from a given structure for unseen categories and indoor scenes. The experimental results show that our method significantly outperforms baseline methods.
title Generate Point Clouds with Multiscale Details from Graph-Represented Structures
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2112.06433