Wenbo Hui

Shanghai University

Papers

1

Total Citations

4

H-Index

1

About

Wenbo Hui is a researcher at the forefront of geometric deep learning and spherical data processing. His primary research focus lies in developing novel convolutional neural network architectures for non-Euclidean domains, particularly for spherical images. Hui’s most notable contribution is the introduction of UVS-CNNs, a framework that constructs general convolutional neural networks on quasi-uniform spherical images. This work addresses the fundamental challenge of applying standard CNNs to spherical data—which suffers from distortion and non-uniform sampling—by enabling efficient, distortion-minimized feature extraction. The UVS-CNNs approach has garnered 4 citations since its publication in 2024, signaling early recognition for its potential in fields such as computer graphics, remote sensing, and 360-degree vision. Hui’s methodology bridges the gap between theoretical geometry and practical deep learning, offering a scalable solution for processing omnidirectional data. His work is particularly impactful for students and researchers exploring alternative CNN architectures beyond planar grids, providing a robust foundation for future advancements in spherical and manifold-based learning.

Research Focus

Key Achievements

1
H-Index
1
Papers
4
Total Citations
4
Avg Citations/Paper
🏆 Most Cited Paper
UVS-CNNs: Constructing general convolutional neural networks on quasi-uniform spherical images
4 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: Shanghai University

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago