Journal
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
Volume -, Issue -, Pages 7202-7211Publisher
IEEE
DOI: 10.1109/ICCV.2019.00730
Keywords
-
Funding
- 973 Program [2015CB351706]
- National Natural Science Foundation of China [U1613219]
- Research Grants Council of the Hong Kong Special Administrative Region
- CUHK [14203416, 14201717]
- Israel Science Foundation [2366/16, 2472/7]
Ask authors/readers for more resources
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 1, 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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available