C
Chenyang Zhu
Researcher at National University of Defense Technology
Publications - 35
Citations - 590
Chenyang Zhu is an academic researcher from National University of Defense Technology. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 11, co-authored 23 publications receiving 352 citations. Previous affiliations of Chenyang Zhu include Simon Fraser University.
Papers
More filters
Journal ArticleDOI
SCORES: shape composition with recursive substructure priors
TL;DR: Results of shape composition from multiple sources over different categories of man-made shapes are shown and compare with state-of-the-art alternatives, demonstrating that the network can significantly expand the range of composable shapes for assembly-based modeling.
Proceedings ArticleDOI
PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation
TL;DR: In this article, a top-down recursive decomposition was proposed for hierarchical segmentation of 3D shapes, based on recursive neural networks, where the decomposition network at all nodes in the hierarchy share weights.
Journal ArticleDOI
Interaction context (ICON): towards a geometric functionality descriptor
TL;DR: A contextual descriptor which aims to provide a geometric description of the functionality of a 3D object in the context of a given scene, which explicitly represents the geometry of object-to-object interactions.
Journal ArticleDOI
Organizing heterogeneous scene collections through contextual focal points
TL;DR: A co-analysis algorithm is presented which interleaves frequent pattern mining and subspace clustering to extract a set of contextual focal points which guide the clustering of the scene collection.
Proceedings ArticleDOI
Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
TL;DR: A novel fusion-aware 3D point convolution which operates directly on the geometric surface being reconstructed and exploits effectively the inter-frame correlation for high-quality 3D feature learning is proposed.