S
Sai-Kit Yeung
Researcher at Hong Kong University of Science and Technology
Publications - 117
Citations - 5116
Sai-Kit Yeung is an academic researcher from Hong Kong University of Science and Technology. The author has contributed to research in topics: Point cloud & Computer science. The author has an hindex of 31, co-authored 102 publications receiving 3259 citations. Previous affiliations of Sai-Kit Yeung include Singapore University of Technology and Design & National University of Singapore.
Papers
More filters
Proceedings ArticleDOI
Pointwise Convolutional Neural Networks
TL;DR: Pointwise convolution as discussed by the authors is a new convolution operator that can be applied at each point of a point cloud, which can yield competitive accuracy in both semantic segmentation and object recognition task.
Proceedings ArticleDOI
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
TL;DR: This paper introduces ScanObjectNN, a new real-world point cloud object dataset based on scanned indoor scene data, and proposes new point cloud classification neural networks that achieve state-of-the-art performance on classifying objects with cluttered background.
Proceedings ArticleDOI
GMS: Grid-Based Motion Statistics for Fast, Ultra-Robust Feature Correspondence
TL;DR: GMS (Grid-based Motion Statistics), a simple means of encapsulating motion smoothness as the statistical likelihood of a certain number of matches in a region, enables translation of high match numbers into high match quality.
Proceedings ArticleDOI
Make it home: automatic optimization of furniture arrangement
TL;DR: A system that automatically synthesizes indoor scenes realistically populated by a variety of furniture objects is presented and whether there is a significant difference in the perceived functionality of the automatically synthesized results relative to furniture arrangements produced by human designers is investigated.
Proceedings ArticleDOI
ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics
TL;DR: This paper proposes an efficient end-to-end permutation invariant convolution for point cloud deep learning and builds an efficient neural network named ShellNet to directly consume the point clouds with larger receptive fields while maintaining less layers.