Shangbin Wu
Papers
1
Total Citations
14
H-Index
1
About
Shangbin Wu is a researcher at the forefront of 3D computer vision and cross-domain feature learning. Their most influential work, "2D3D-MVPNet," introduces a novel framework for learning robust feature descriptors that bridge the gap between 2D images and 3D point clouds. By leveraging multi-view projections of point clouds, Wu’s approach enables accurate 2D-3D matching, a critical capability for applications in augmented reality, robotics, and autonomous navigation. This paper has garnered 14 citations since its 2022 publication, signaling growing recognition in the field. Wu’s contributions address a fundamental challenge in computer vision: aligning disparate data representations to enable seamless interaction between real-world scenes and digital models. Their work stands out for its practical impact, offering a scalable solution that enhances the reliability of feature correspondence across modalities. As the demand for robust 3D perception systems grows, Wu’s research continues to inspire new directions in multi-modal learning and geometric deep learning.
Research Focus
Key Achievements
Top Papers
- 1