Haiyong Jiang

8

Papers

1

Total Citations

Papers (8)

Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent Visibility

D^3CTTA: Domain-Dependent Decorrelation for Continual Test-Time Adaption of 3D LiDAR Segmentation

Activating Sparse Part Concepts for 3D Class Incremental Learning

SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation

NeurIPS 2025arXiv

End-to-End 3D Point Cloud Instance Segmentation Without Detection

VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation

CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

Decompose Novel into Known: Part Concept Learning For 3D Novel Class Discovery