Xiankun Zhou
Papers
1
Total Citations
2
H-Index
1
About
Xiankun Zhou is a researcher whose work lies at the intersection of 3D computer vision, deep learning, and autonomous perception. His primary contributions center on advancing scene flow estimation—a critical task for understanding dynamic environments in applications like self-driving cars and robotics. Zhou is best known for developing PVFT-Net, a novel point-voxel fusion method that integrates transformer architectures for self-supervised scene flow estimation. This approach, detailed in his 2025 paper, addresses key challenges in handling irregular point cloud data while maintaining computational efficiency, offering a robust solution for real-time 3D motion analysis. Though early in its citation trajectory, this work has already garnered attention for its innovative fusion of point-based and voxel-based representations, bridging a gap in existing methods. Zhou’s research demonstrates a clear focus on pushing the boundaries of self-supervised learning in 3D perception, with potential impacts on autonomous navigation and scene understanding. His work reflects a growing trend toward leveraging transformers for spatial-temporal reasoning in unstructured data, positioning him as an emerging voice in the field.
Research Focus
Key Achievements
Top Papers
- 1