X
Xianzhi Li
Researcher at The Chinese University of Hong Kong
Publications - 22
Citations - 1565
Xianzhi Li is an academic researcher from The Chinese University of Hong Kong. The author has contributed to research in topics: Point cloud & Upsampling. The author has an hindex of 11, co-authored 22 publications receiving 677 citations.
Papers
More filters
Proceedings ArticleDOI
PU-Net: Point Cloud Upsampling Network
TL;DR: A data-driven point cloud upsampling technique to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space, which shows that its upsampled points have better uniformity and are located closer to the underlying surfaces.
Book ChapterDOI
EC-Net: An Edge-Aware Point Set Consolidation Network
TL;DR: This paper presents the first deep learning based edge-aware technique to facilitate the consolidation of point clouds, and trains the network to process points grouped in local patches, and train it to learn and help consolidate points, deliberately for edges.
Proceedings ArticleDOI
PU-GAN: A Point Cloud Upsampling Adversarial Network
TL;DR: Li et al. as discussed by the authors presented 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.
Posted Content
PU-GAN: a Point Cloud Upsampling Adversarial Network.
TL;DR: 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.
Journal ArticleDOI
Attention GANs: Unsupervised Deep Feature Learning for Aerial Scene Classification
Yunlong Yu,Xianzhi Li,Fuxian Liu +2 more
TL;DR: Experimental results demonstrate that the novel unsupervised deep feature learning method, namely, Attention generative adversarial networks (Attention GANs), can obtain the best performance compared with the state-of-the-art methods.