Progressive Point Cloud Upsampling via Differentiable Rendering

Pingping ZHANG, Xu WANG, Lin MA, Shiqi WANG, Sam KWONG, Jianmin JIANG

Research output: Journal PublicationsJournal Article (refereed)peer-review

16 Citations (Scopus)

Abstract

In this paper, we propose one novel progressive point cloud upsampling framework to tackle the non-uniform distribution issue during the point cloud upsampling process. Specifically, we design an Up-UNet feature expansion module which is capable of learning the local and global point features via a down-feature operator and an up-feature operator, respectively, to alleviate the non-uniform distribution issue and remove the outliers. Moreover, we design a hybrid loss function considering both the multi-scale reconstruction loss and the rendering loss. The multi-scale reconstruction loss enables each upsampling module to generate a denser point cloud, while the rendering loss via point-based differentiable rendering ensures that the proposed model preserves the point cloud structures. Extensive experimental results demonstrate that our proposed model achieves state-of-the-art performance in terms of both qualitative and quantitative evaluations.
Original languageEnglish
Pages (from-to)4673-4685
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume31
Issue number12
Early online date26 Jul 2021
DOIs
Publication statusPublished - Dec 2021
Externally publishedYes

Keywords

  • feature expansion unit
  • Point cloud upsampling
  • point-based differential rendering

Fingerprint

Dive into the research topics of 'Progressive Point Cloud Upsampling via Differentiable Rendering'. Together they form a unique fingerprint.

Cite this