William (Bill) Peebles

email: peebles [at] berkeley [dot] edu

Recent Research

Check out our recent work on using GANs to train vision models.

About Me

I'm a third-year PhD student at UC Berkeley advised by Alyosha Efros. Previously, I did my undergrad at MIT where I worked with Antonio Torralba. My research focuses on deep learning and artificial intelligence, most notably unsupervised learning and deep generative models. I've interned at FAIR, Adobe Research and NVIDIA. I'm supported by the National Science Foundation's Graduate Research Fellowship Program.

News

[Jun 2022] GANgealing is a best paper finalist at CVPR'22.
[Apr 2022] Check out Two Minute Papers' video covering GANgealing!
[Mar 2022] GANgealing has been accepted as an Oral at CVPR'22.
[Dec 2021] A mixed reality Colab demo powered by GANgealing is available here.
[Dec 2021] GANgealing PyTorch code and pre-trained models are available here.
[Aug 2020] Code for the Hessian Penalty has been released in PyTorch and TensorFlow here.

Publications

GAN-Supervised Dense Visual Alignment
William Peebles, Jun-Yan Zhu, Richard Zhang, Antonio Torralba, Alexei Efros, Eli Shechtman
CVPR 2022 (Oral) · Best Paper Finalist
two minute papers · mixed reality demo · video · project page · paper · github

The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement
William Peebles, John Peebles, Jun-Yan Zhu, Alexei Efros, Antonio Torralba
ECCV 2020 (Spotlight)
video · overview in 90 seconds · project page · paper · github

GAN reconstructions of images versus the original images. Seeing What a GAN Cannot Generate
David Bau, Jun-Yan Zhu, Jonas Wulff, William Peebles, Hendrik Strobelt, Bolei Zhou, Antonio Torralba
ICCV 2019 (Oral)
demo · paper · overview · github

A natural image of a building is modified by adding trees and domes. Semantic Photo Manipulation with a Generative Image Prior
David Bau, Hendrik Strobelt, William Peebles, Jonas Wulff, Bolei Zhou, Jun-Yan Zhu, Antonio Torralba
SIGGRAPH 2019
demo · paper · overview