“Neuralize” geometry processing pipeline

Yifan Wang


Please LOG IN to view the video.

Date: March 9, 2022


Fueled by the proliferation of consumer-level 3D acquisition devices and the growing accessibility of shape modeling applications for ordinary users, there is a tremendous need for automatic geometry processing algorithms that perform robustly even under incomplete and distorted data. This talk demonstrates how each step of the geometry processing pipeline can be automated and, more importantly, strengthened by utilizing neural networks to leverage consistencies and high-level semantic priors from data.

Further Information:

Yifan is an incoming post-doc researcher at the Stanford Computational Imaging Lab. She obtained her Ph.D.  from the Interactive Geometry Lab at ETH Zurich, where she revamped many well-known geometry processing tasks using neural networks. Her work lies in the intersection between computer vision, graphics, and machine learning, spanning a wide range of topics.

Created: Thursday, March 17th, 2022