Gene Chou

I am starting my PhD in September at Cornell University, where I will be advised by Noah Snavely and Bharath Hariharan. Previously, I was a research assistant in the Princeton Computational Imaging Lab, advised by Felix Heide. I received my bachelor's in computer science and math from Princeton University. My research interests are broadly in 3D scene representations.

Contact: gc492@cornell.edu

CV  /  Github  /  LinkedIn  /  pictures of my cat

Research

I am currently working on scene understanding + RL for robot navigation and sim-to-real transfer at Disney Research.


Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions
Gene Chou, Yuval Bahat, Felix Heide
Arxiv preprint
paper / code / project page / teaser video

This work performs diffusion on the weights of neural SDFs while providing geometric guidance. It generates diverse meshes conditioned on partial point clouds, 2D images, and real-scanned point clouds.

GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions
Gene Chou, Ilya Chugunov, Felix Heide
NeurIPS 2022 (Featured)
paper / code / project page

State-of-the-art methods for neural SDF estimation struggle to fit more than a few shapes at a time. This work presents a two stage semi-supervised meta-learning approach to reconstruct SDFs from raw input point clouds of over a hundred unseen object classes.

Curriculum Vitae


Website template borrowed from Jon Barron.