Weng Fei Low
Papers
1
Total Citations
6
H-Index
1
About
Weng Fei Low is a researcher at the forefront of geometric deep learning and neural surface representation. His work focuses on developing efficient, parameterized models for complex 3D shapes, with a particular emphasis on minimizing both the number of charts and geometric distortion in neural atlases. Low’s most-cited contribution, "Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion" (2022), introduces a novel framework that learns compact, distortion-aware mappings for arbitrary surfaces, significantly advancing the state of the art in neural surface parameterization. This work has garnered 6 citations, establishing a foundation for subsequent research in differentiable rendering and 3D reconstruction. By tackling the longstanding challenge of balancing chart count with geometric fidelity, Low’s approach enables more efficient and accurate representation of complex topologies, with implications for computer graphics, medical imaging, and autonomous systems. His research bridges the gap between classical differential geometry and modern deep learning, offering practical tools for real-world 3D modeling tasks. Low’s contributions are particularly notable for their elegance and direct applicability, making him a rising voice in the geometric deep learning community.
Research Focus
Key Achievements
Top Papers
- 1