Generate Point Clouds with Multiscale Details from Graph-Represented Structures

13 Dec 2021  ·  Ximing Yang, Zhengfu He, Cheng Jin ·

As details are missing in most representations of structures, the lack of controllability to details 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 local 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. By editing the MSG, the proposed method supports multiscale editions on point clouds. 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 is able to 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.

PDF Abstract

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here