Jane Wu

I am a Postdoctoral Fellow in the Electrical Engineering and Computer Science Department at UC Berkeley, advised by Jitendra Malik and funded by the UC President's Postdoctoral Fellowship and the NSF Mathematical Sciences Postdoctoral Research Fellowship. My research is focused primarily on designing machine learning models that reason about the geometry and dynamics of the physical 3D world, with applications in AR/VR and robotics.

I received my Ph.D. in Computer Science from Stanford University, where I was advised by Ron Fedkiw in the Stanford AI Lab. During my Ph.D., I was a student researcher at Google in the Project Starline team and a part-time R&D software engineer and intern at NVIDIA. I also served as co-chair of Stanford Grad WiCS.

Email: janehwu@berkeley.edu
[CV] [Google Scholar]

Recent Publications

Hand-Object Interaction Pretraining from Videos

Himanshu Gaurav Singh, Antonio Loquercio, Carmelo Sferrazza, Jane Wu, Haozhi Qi, Pieter Abbeel, Jitendra Malik, arXiv:2409.08273 Preprint, September 2024.

[arXiv] [website] [code]
Reconstructing Hand-Held Objects in 3D

Jane Wu, Georgios Pavlakos, Georgia Gkioxari, Jitendra Malik, arXiv:2404.06507 Preprint, April 2024.

[arXiv] [website] [code]
Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion

Kira Prabhu, Jane Wu, Lynn Tsai, Peter Hedman, Dan B Goldman, Ben Poole, Michael Broxton, arXiv:2312.03869 Preprint, December 2023.

[arXiv] [website]
Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Maps

Jane Wu, Diego Thomas, Ron Fedkiw, arXiv:2311.16042 Preprint, November 2023.

[arXiv]
HazardNet: Road Debris Detection by Augmentation of Synthetic Models

Tae Eun Choe, Jane Wu, Xiaolin Lin, Karen Kwon, Minwoo Park, CVPR Workshop on Autonomous Driving (WAD), June 2023.

[arXiv] [pdf]
Skinning a Three-Dimensional Framework for Neural Network Cloth

Jane Wu, Zhenglin Geng, Hui Zhou, Ron Fedkiw, arXiv:2006.04874 Preprint, June 2020.

[arXiv]
Recovering Geometric Information with Learned Texture Perturbations

Jane Wu, Yongxu Jin, Zhenglin Geng, Hui Zhou, Ron Fedkiw, ACM SIGGRAPH/Eurographics Symposium on Computer Animation (SCA), September 2021.

[arXiv] [pdf]
Deep Energies for Estimating Facial Pose and Expression

Jane Wu, Michael Bao, Xinwei Yao, Ron Fedkiw, Communications on Applied Mathematics and Computation, March 2023, and arXiv:1812.02899 Preprint, November 2018.

[arXiv] [pdf]