Bio

Ningna Wang is a Postdoctoral Research Scientist at Columbia University, where her research focuses on 3D geometry processing with an emphasis on compact and interpretable shape representations. Her work has been presented at ACM SIGGRAPH and SIGGRAPH Asia, earning broad recognition including a Best Paper Award at SIGGRAPH 2023. She received her Ph.D. in Computer Science from the University of Texas at Dallas. Before her doctoral studies, she worked as a Senior Software Developer at Booking.com in Amsterdam. She also holds an M.S. from Carnegie Mellon University and a B.S. from Jilin University in China. Her research has recently been recognized through the WiGRAPH Rising Stars (2025) and the MIT EECS Rising Stars (2025).

Geometric Representations for Efficient and Intelligent 3D Understanding

Efficient storage and processing of 3D geometric data is essential to unlocking the full potential of recent advances in artificial intelligence. My research develops compact and expressive representations of 3D geometry that support both human understanding and machine reasoning.

I explore skeletal abstractions such as the medial axis to capture intrinsic shape properties including symmetry, topology, and part decomposition, while also advancing algorithms for standard representations like meshes and point clouds. These representations uncover perceptually meaningful organization and serve as effective priors for optimization, editing, and generative modeling. For example, I have introduced topology preserving medial representations and structure aware algorithms that enable robust reconstruction, analysis, and manipulation of complex 3D data.

Beyond geometric abstraction, my broader goal is to bridge geometry processing with learning-based approaches. By combining geometric reasoning with data-driven methods, I aim to design representations that are not only efficient but also generalizable across tasks. This synergy enables high-level shape understanding, supports controllable generative models, and facilitates interactive design tools.

Looking forward, I envision geometric abstraction as a foundation for more intuitive and intelligent 3D interaction, powering applications in computer graphics, computational design, robotics, and beyond. My work strives to make 3D data more accessible, interpretable, and actionable, ultimately connecting low-level geometric detail with high-level semantic understanding.