Profile Photo

Postdoc @ Stanford University

Email: szwu AT cs.stanford.edu

Elliott / Shangzhe Wu


I will be joining the Department of Engineering at the University of Cambridge as an Assistant Professor in March 2025. I'm building a research group focusing on modeling the dynamic physical 3D world from images and will be looking for PhD students to start in October 2025. If you are interested in joining us and have experience in 3D computer vision, generative models, and/or computer graphics, please apply to the Engineering PhD Program by the funding deadline on December 3, 2024.

I am currently a postdoc researcher at Stanford University, working with Jiajun Wu. My current research focuses on unsupervised 3D learning and inverse rendering. I'm particularly fascinated by symmetries and structures in nature, as well as how they connect to the way we make sense of our perceptual experiences. The fundamental motivation behind my work is to build generative models of the physical natural world, capturing distributions of physical properties (e.g., 3D shape, motion, reflectance) from raw, casual multimodal observations (e.g., Internet photos, videos, audio) without direct supervision.

I obtained my PhD from Oxford VGG, advised by Andrea Vedaldi and Christian Rupprecht, and BSc in Computer Science from HKUST, working with Chi-Keung Tang and Yu-Wing Tai. I also spent a lovely summer interning at Google Research with Noah Snavely's team.


News:

Oct 2024: Humbled to received the ECVA PhD Award!

Sep 2024: We are organizing a Workshop on Visual Concepts at ECCV 2024.

Jun 2024: We are organizing the 4th CV4Animals Workshop at CVPR 2024.

Nov 2023: Honored to received the BMVA Sullivan Doctoral Thesis Prize!

Dec 2022: Defended my PhD thesis on Unsupervised Learning of 3D Objects in the Wild!

Oct 2022: Collected another two Outstanding Reviewer badges from ECCV and NeurIPS!

Oct 2022: We are organizing an ECCV Workshop on Neural Geometry and Rendering with the CO3D Challenge.

Oct 2021: We are organizing an ICCV Workshop on Unsupervised 3D Learning in the Wild.

Jun 2021: I have set up some public office hours (following Jia-Bin Huang).

May 2021: Happy to be recognized as an Outstanding Reviewer at CVPR 2021!

Jun 2020: Our work on Unsup3D received the Best Paper Award at CVPR 2020!


Recent Talks:

[2024/05] Physical Natural World from Images

[2023/12] Learning 3D Fauna and Flora in the Wild


PUBLICATIONS


( * and indicate equal contribution or alphabetical order )


RESEARCH × ART



PUBLIC OFFICE HOURS


( This may take a while to load. Try refreshing the page if it's not loading. )