Deep Magnification-Flexible Upsampling over 3D Point Clouds

Yue QIAN, Junhui HOU, Sam KWONG, Ying HE

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

33 Citations (Scopus)


This paper addresses the problem of generating dense point clouds from given sparse point clouds to model the underlying geometric structures of objects/scenes. To tackle this challenging issue, we propose a novel end-to-end learning-based framework. Specifically, by taking advantage of the linear approximation theorem, we first formulate the problem explicitly, which boils down to determining the interpolation weights and high-order approximation errors. Then, we design a lightweight neural network to adaptively learn unified and sorted interpolation weights as well as the high-order refinements, by analyzing the local geometry of the input point cloud. The proposed method can be interpreted by the explicit formulation, and thus is more memory-efficient than existing ones. In sharp contrast to the existing methods that work only for a predefined and fixed up sampling factor, the proposed framework only requires a single neural network with one-time training to handle various up sampling factors within a typical range, which is highly desired in real-world applications. In addition, we propose a simple yet effective training strategy to drive such a flexible ability. In addition, our method can handle non-uniformly distributed and noisy data well. Extensive experiments on both synthetic and real-world data demonstrate the superiority of the proposed method over state-of-the-art methods both quantitatively and qualitatively. The code will be publicly available at
Original languageEnglish
Pages (from-to)8354-8367
JournalIEEE Transactions on Image Processing
Early online date30 Sept 2021
Publication statusPublished - 2021
Externally publishedYes


  • deep learning
  • linear approximation
  • Point cloud
  • sampling
  • surface reconstruction


Dive into the research topics of 'Deep Magnification-Flexible Upsampling over 3D Point Clouds'. Together they form a unique fingerprint.

Cite this