PU-Flow : a Point Cloud Upsampling Network with Normalizing Flows

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations


  • Aihua Mao
  • Zihui Du
  • Yaqi Duan
  • Yong-jin Liu
  • Ying He


Original languageEnglish
Number of pages14
Journal / PublicationIEEE Transactions on Visualization and Computer Graphics
Online published4 Aug 2022
Publication statusOnline published - 4 Aug 2022


Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets. To address this issue, we present a novel deep learning-based model, called PU-Flow, which incorporates normalizing flows and weight prediction techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we exploit the invertible characteristics of normalizing flows to transform points between Euclidean and latent spaces and formulate the upsampling process as ensemble of neighbouring points in a latent space, where the ensemble weights are adaptively learned from local geometric context. Extensive experiments show that our method is competitive and, in most test cases, it outperforms state-of-the-art methods in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency. The source code will be publicly available at https://github.com/unknownue/puflow.

Research Area(s)

  • Feature extraction, Interpolation, normalizing flows, Pipelines, Point cloud analysis, Point cloud compression, Surface treatment, Task analysis, Three-dimensional displays, upsampling, weight prediction