Generate Point Clouds with Multiscale Details from Graph-Represented Structures

12/13/2021
by   Ximing Yang, et al.
0

Generating point clouds from structures is a highly valued method to control the generation of point clouds.One of the major problems in structure-based controllable point cloud generation is the lack of controllability to details, as details are missing in most existing representations of structures.It can be observed that definitions of details and structures are subjective.Details can be treated as structures on small scale.To represent structures in different scales at the same time, we present a graph-based representation of structures called the Multiscale Structure Graph(MSG).By treating details as small-scale structures, similar patterns of local structures can be found at different scales, places, densities, and angles.The knowledge learned from a pattern can be transferred to similar patterns in other scales.An encoding and generation mechanism, namely the Multiscale Structure-based Point Cloud Generator(MSPCG), for generating dense point clouds from the MSG is proposed, which can simultaneously learn local patterns with miscellaneous spatial properties.Our MSPCG also has great generalization ability and scalability.An MSPCG trained on the ShapeNet dataset can enable multi-scale edition on point clouds, generate point clouds for unseen categories, and generate indoor scenes from a given structure. The experimental results show that our method significantly outperforms baseline methods.

READ FULL TEXT

page 3

page 8

research
05/30/2022

CompleteDT: Point Cloud Completion with Dense Augment Inference Transformers

Point cloud completion task aims to predict the missing part of incomple...
research
03/29/2023

TriVol: Point Cloud Rendering via Triple Volumes

Existing learning-based methods for point cloud rendering adopt various ...
research
04/10/2018

Classification of Point Cloud Scenes with Multiscale Voxel Deep Network

In this article we describe a new convolutional neural network (CNN) to ...
research
08/20/2019

Developing Creative AI to Generate Sculptural Objects

We explore the intersection of human and machine creativity by generatin...
research
09/23/2021

Multi-resolution deep learning pipeline for dense large scale point clouds

Recent development of 3D sensors allows the acquisition of extremely den...
research
07/29/2022

A Graph Theoretic Exploration of Coronary Vascular Trees

The aim of this study was to automate the generation of small coronary v...
research
07/08/2019

Learning Structural Graph Layouts and 3D Shapes for Long Span Bridges 3D Reconstruction

A learning-based 3D reconstruction method for long-span bridges is propo...

Please sign up or login with your details

Forgot password? Click here to reset