PU-GAN: A point cloud upsampling adversarial network

Ruihui Li, Xianzhi Li, Chi Wing Fu, Daniel Cohen-Or, Pheng Ann Heng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Point clouds acquired from range scans are often sparse, noisy, and non-uniform. This paper presents a new point cloud upsampling network called PU-GAN, which is formulated based on a generative adversarial network (GAN), to learn a rich variety of point distributions from the latent space and upsample points over patches on object surfaces. To realize a working GAN network, we construct an up-down-up expansion unit in the generator for upsampling point features with error feedback and self-correction, and formulate a self-attention unit to enhance the feature integration. Further, we design a compound loss with adversarial, uniform and reconstruction terms, to encourage the discriminator to learn more latent patterns and enhance the output point distribution uniformity. Qualitative and quantitative evaluations demonstrate the quality of our results over the state-of-the-arts in terms of distribution uniformity, proximity-to-surface, and 3D reconstruction quality.

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Computer Vision, ICCV 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages10
ISBN (Electronic)9781728148038
StatePublished - Oct 2019
Event17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 - Seoul, Korea, Republic of
Duration: 27 Oct 20192 Nov 2019

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499


Conference17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Country/TerritoryKorea, Republic of


FundersFunder number
National Natural Science Foundation of China
Israel Science Foundation2366/16, 2472/7
Chinese University of Hong Kong14201717, 14203416
National Basic Research Program of China (973 Program)2015CB351706


    Dive into the research topics of 'PU-GAN: A point cloud upsampling adversarial network'. Together they form a unique fingerprint.

    Cite this