| CARVIEW |
Assistant Professor
University of Cambridge
Email: sw2181 AT cam.ac.uk
Office: BE454, Baker Building
Elliott / Shangzhe Wu
I am an Assistant Professor in the Department of Engineering at the University of Cambridge. I'm building a research team focused on computer vision and dynamic 3D world modeling, with applications across controllable generative media, robotics, and biology. Our goal is to model the dynamic physical 3D world from raw, sparse, and multimodal observations, including images, videos, and audio.
Previously, I was a postdoc at Stanford University, working with Jiajun Wu. I completed my PhD in the Visual Geometry Group (VGG) at the University of Oxford, advised by Andrea Vedaldi and Christian Rupprecht, and my BSc in Computer Science from HKUST, where I worked with Chi-Keung Tang and Yu-Wing Tai.
Elliott (Shangzhe) Wu is an Assistant Professor at the Department of Engineering, University of Cambridge. He received his PhD from the University of Oxford, advised by Andrea Vedaldi and Christian Rupprecht, and worked as a postdoc at Stanford University with Jiajun Wu. His research focuses on 3D computer vision and inverse graphics. His work received several awards, including the Best Paper Award at CVPR 2020, the BMVA Sullivan Doctoral Thesis Prize, and the ECVA PhD Award.
[09/2025]: I'm looking for two (fully funded) PhD students and potentially a postdoc to join our team in fall 2026. If you're passionate about any of the following topics and have relevant experience, please apply to the PhD in Engineering program by early December:
- multi-modal spatial modeling (vision, language, audio, etc.)
- vision-based robot learning (e.g., real-to-sim-to-real)
- 3D/4D modelling of biological systems across scales (molecules, cells, animals, etc.)
Feel free to reach out by emails, but I'll likely only be able to review applications in late December.
PhD Applicants:
Please apply to the PhD in Engineering program by the funding deadline—typically in early December for entry the following fall. You will be able to indicate whether you wish to be considered for various scholarships in the application form. Once indicated, you will be automatically entered into the central funding competition.
A few scholarships may require separate applications, such as the Gates Cambridge Scholarship (deadline in mid-October for US citizens and early December for others), the Peterhouse Postgraduate Studentships, and many external scholarships listed here. You can also check out the ELLIS PhD program for co-supervision (deadline in late October).
Important: Your application will only be processed once all required recommendation letters have been received. Please ensure that your referees submit their letters by the application deadline.
Postdoc and Research Fellows:
Check out fellowship programs such as:
- Cambridge Trinity College Junior Research Fellowships (JRF) — deadline around August
- Marie Skłodowska-Curie Actions (MSCA) Postdoctoral Fellowships — deadline around September
- Newton International Fellowships (NIF) — deadline around March
- Turing AI Pioneer Interdisciplinary Fellowships — deadline around October
- Schmidt Science Fellowships — requires nomination from your home institution, deadline around May
Feel free to email me your CV if you're planning to apply.
Cambridge Undergraduate and Master's Students:
I regularly supervise Engineering IIB (selection around May) and MLMI MPhil projects (selection around March). Feel free to subscribe to the Computer Vision Seminars mailing list.
Other Visiting Students / Research Interns:
I do not host remote interns. If you're interested in visiting us in person for a few months, please email me with your CV and answers to the following questions:
- When do you plan to visit (preferably 6-12 months)?
- Will your current advisor be involved?
- Who will fund your visit? Note that Cambridge charges an extra bench fee of £~1K/month (unless your home institution has an existing reciprocal fee-free exchange agreement with Cambridge).
- What do you plan to work on?
Highlights:
[09/2025]: I'm looking for two (fully funded) PhD students and potentially a postdoc to join our team in fall 2026. See "Positions" above for details.
[06/2025]: We are organizing three workshops at CVPR 2025: the Workshop on 4D Vision, the 5th CV4Animals Workshop, and the 2nd Workshop on Visual Concepts.
[10/2024]: Humbled to receive the ECVA PhD Award!
[11/2023]: Honored to receive the BMVA Sullivan Doctoral Thesis Prize!
[06/2020]: Our work on Unsupervised 3D 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
Research Team
Chexuan Qiao
PhD, Cambridge
(with Roberto Cipolla)
Yuxin Yao
PhD, Cambridge
(with Joan Lasenby)
Shenhan Qian
ELLIS PhD, TUM
(with Daniel Cremers)
Ray / Ruining Li
Visiting PhD, Oxford
(with Andrea Vedaldi & Christian Rupprecht)
Xiaoyang Lyu
Visiting PhD, HKU
Is that you?
PhD, Cambridge
2026-
Publications
( * and † indicate equal contribution or alphabetical order )
-
Particulate: Feed-Forward 3D Object Articulation
Ruining Li*, Yuxin Yao*, Chuanxia Zheng, Christian Rupprecht, Joan Lasenby†, Shangzhe Wu†, Andrea Vedaldi†
arXiv preprint 2025
Page
Demo
Paper
Code
@Article{li2025particulate, title = {{Particulate}: Feed-Forward 3D Object Articulation}, author = {Ruining Li and Yuxin Yao and Chuanxia Zheng and Christian Rupprecht and Joan Lasenby and Shangzhe Wu and Andrea Vedaldi}, journal = {arXiv preprint arXiv:2512.11798}, year = {2025} } -
Web-Scale Collection of Video Data for 4D Animal Reconstruction
Brian Nlong Zhao, Jiajun Wu†, Shangzhe Wu†
NeurIPS (Datasets and Benchmarks Track) 2025
Paper
Code
@InProceedings{zhao2025animalvideo, title = {Web-Scale Collection of Video Data for 4D Animal Reconstruction}, author = {Brian Nlong Zhao and Jiajun Wu and Shangzhe Wu}, booktitle = {NeurIPS Datasets and Benchmarks Track}, year = {2025} } -
🪄 Anymate: A Dataset and Baselines for Learning 3D Object Rigging
Yufan Deng*, Yuhao Zhang*, Chen Geng, Shangzhe Wu†, Jiajun Wu†
SIGGRAPH 2025
Page
Demo
Paper
Code
@InProceedings{deng2025anymate, title = {{Anymate}: A Dataset and Baselines for Learning 3D Object Rigging}, author = {Yufan Deng and Yuhao Zhang and Chen Geng and Shangzhe Wu and Jiajun Wu}, booktitle = {SIGGRAPH}, year = {2025} } -
Category-Agnostic Neural Object Rigging
Guangzhao He*, Chen Geng*, Shangzhe Wu, Jiajun Wu
CVPR 2025
Page
Paper
@InProceedings{he2025canor, title = {Category-Agnostic Neural Object Rigging}, author = {Guangzhao He and Chen Geng and Shangzhe Wu and Jiajun Wu}, booktitle = {CVPR}, year = {2025} } -
🥀 Birth and Death of a Rose
Chen Geng, Yunzhi Zhang, Shangzhe Wu, Jiajun Wu
CVPR 2025 (Oral)
Page
Paper
@InProceedings{geng2025rose4d, title = {Birth and Death of a Rose}, author = {Chen Geng and Yunzhi Zhang and Shangzhe Wu and Jiajun Wu}, booktitle = {CVPR}, year = {2025} } -
DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction
Ben Kaye*, Tomas Jakab*, Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
CVPR 2025 (Highlight)
Page
Paper
Code
@InProceedings{kaye2025dualpm, title = {{DualPM}: Dual Posed-Canonical Point Maps for {3D} Shape and Pose Reconstruction}, author = {Ben Kaye and Tomas Jakab and Shangzhe Wu and Christian Rupprecht and Andrea Vedaldi}, booktitle = {CVPR}, year = {2025} } -
The Scene Language: Representing Scenes with Programs, Words, and Embeddings
Yunzhi Zhang, Zizhang Li, Matt Zhou, Shangzhe Wu, Jiajun Wu
CVPR 2025 (Highlight)
Page
Paper
Code
@InProceedings{zhang2025scenelang, title = {The Scene Language: Representing Scenes with Programs, Words, and Embeddings}, author = {Yunzhi Zhang and Zizhang Li and Matt Zhou and Shangzhe Wu and Jiajun Wu}, booktitle = {CVPR}, year = {2025} } -
🐎 Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos
Keqiang Sun*, Dor Litvak*, Yunzhi Zhang, Hongsheng Li, Jiajun Wu†, Shangzhe Wu†
ECCV 2024
Page
Video
Paper
Code
@InProceedings{sun2024ponymation, title = {{Ponymation}: Learning Articulated 3D Animal Motions from Unlabeled Online Videos}, author = {Keqiang Sun and Dor Litvak and Yunzhi Zhang and Hongsheng Li and Jiajun Wu and Shangzhe Wu}, booktitle = {ECCV}, year = {2024} } -
🎧 Hearing Anything Anywhere
Mason L. Wang*, Ryosuke Sawata*, Samuel Clarke, Ruohan Gao, Shangzhe Wu, Jiajun Wu
CVPR 2024
Page
Video
Paper
Code
@InProceedings{wang2024hearing, title = {Hearing Anything Anywhere}, author = {Mason Wang and Ryosuke Sawata and Samuel Clarke and Ruohan Gao and Shangzhe Wu and Jiajun Wu}, booktitle = {CVPR}, year = {2024} } -
🐏 🐕 🐁 🦌 Learning the 3D Fauna of the Web
Zizhang Li*, Dor Litvak*, Ruining Li, Yunzhi Zhang, Tomas Jakab, Christian Rupprecht, Shangzhe Wu†, Andrea Vedaldi†, Jiajun Wu†
CVPR 2024
Page
Demo
Paper
Code
@InProceedings{li2024fauna, title = {Learning the 3D Fauna of the Web}, author = {Zizhang Li and Dor Litvak and Ruining Li and Yunzhi Zhang and Tomas Jakab and Christian Rupprecht and Shangzhe Wu and Andrea Vedaldi and Jiajun Wu}, booktitle = {CVPR}, year = {2024} } -
Language-Informed Visual Concept Learning
Sharon Lee*, Yunzhi Zhang*, Shangzhe Wu, Jiajun Wu
ICLR 2024
Page
Paper
Code
@InProceedings{lee2024visualconcepts, title = {Language-Informed Visual Concept Learning}, author = {Sharon Lee and Yunzhi Zhang and Shangzhe Wu and Jiajun Wu}, booktitle = {ICLR}, year = {2024} } -
Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark
Zhengfei Kuang*, Yunzhi Zhang*, Hong-Xing Yu, Samir Agarwala, Shangzhe Wu, Jiajun Wu
NeurIPS (Datasets and Benchmarks Track) 2023
Page
Paper
Code
@InProceedings{kuang2023stanfordorb, title = {{Stanford-ORB}: A Real-World 3D Object Inverse Rendering Benchmark}, author = {Zhengfei Kuang and Yunzhi Zhang and Hong-Xing Yu and Samir Agarwala and Shangzhe Wu and Jiajun Wu}, booktitle = {NeurIPS Datasets and Benchmarks Track}, year = {2023} } -
🐄 Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion
Tomas Jakab*, Ruining Li*, Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
3DV 2024
Page
Paper
Code
@InProceedings{jakab2024farm3d, title = {{Farm3D}: Learning Articulated 3D Animals by Distilling 2D Diffusion}, author = {Tomas Jakab and Ruining Li and Shangzhe Wu and Christian Rupprecht and Andrea Vedaldi}, booktitle = {3DV}, year = {2024} } -
🌹 Seeing a Rose in Five Thousand Ways
Yunzhi Zhang, Shangzhe Wu, Noah Snavely, Jiajun Wu
CVPR 2023
Page
Paper
Code
@InProceedings{zhang2023rose, title = {Seeing a Rose in Five Thousand Ways}, author = {Yunzhi Zhang and Shangzhe Wu and Noah Snavely and Jiajun Wu}, booktitle = {CVPR}, year = {2023} } -
🎠 MagicPony: Learning Articulated 3D Animals in the Wild
Shangzhe Wu*, Ruining Li*, Tomas Jakab*, Christian Rupprecht, Andrea Vedaldi
CVPR 2023
Page
Video
Paper
Code
@InProceedings{wu2023magicpony, title = {{MagicPony}: Learning Articulated 3D Animals in the Wild}, author = {Shangzhe Wu and Ruining Li and Tomas Jakab and Christian Rupprecht and Andrea Vedaldi}, booktitle = {CVPR}, year = {2023} } -
Unsupervised Learning of 3D Objects in the Wild
Shangzhe Wu
DPhil Thesis, University of Oxford, 2022
ECVA PhD Award, and BMVA Sullivan Doctoral Thesis Prize
Thesis
@phdthesis{wu2022thesis, title = {Unsupervised Learning of 3D Objects in the Wild}, author = {Shangzhe Wu}, school = {University of Oxford}, year = {2022} } -
Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
Keqiang Sun*, Shangzhe Wu*, Zhaoyang Huang, Ning Zhang, Quan Wang, Hongsheng Li
NeurIPS 2022 (Spotlight), also in TPAMI 2023
Page
Paper
Paper (TPAMI)
Code
@InProceedings{sun2022cgof, title = {Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields}, author = {Keqiang Sun and Shangzhe Wu and Zhaoyang Huang and Ning Zhang and Quan Wang and HongSheng Li}, booktitle = {NeurIPS}, year = {2022} } -
De-rendering 3D Objects in the Wild
Felix Wimbauer, Shangzhe Wu, Christian Rupprecht
CVPR 2022
Page
Video
Paper
Code
@InProceedings{wimbauer2022derender, title = {De-rendering 3D Objects in the Wild}, author = {Felix Wimbauer and Shangzhe Wu and Christian Rupprecht}, booktitle = {CVPR}, year = {2022} } -
🕊 DOVE: Learning Deformable 3D Objects by Watching Videos
Shangzhe Wu*, Tomas Jakab*, Christian Rupprecht, Andrea Vedaldi
IJCV 2023
Page
Video
Paper
Code
@Article{wu2023dove, title = {{DOVE}: Learning Deformable 3D Objects by Watching Videos}, author = {Shangzhe Wu and Tomas Jakab and Christian Rupprecht and Andrea Vedaldi}, journal = {IJCV}, year = {2023} } -
NeRF--: Neural Radiance Fields Without Known Camera Parameters
Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, Victor Adrian Prisacariu
arXiv preprint 2021
Page
Paper
Code
@Article{wang2021nerfmm, title = {{NeRF}$--$: Neural Radiance Fields Without Known Camera Parameters}, author = {Zirui Wang and Shangzhe Wu and Weidi Xie and Min Chen and Victor Adrian Prisacariu}, journal = {arXiv preprint arXiv:2102.07064}, year = {2021} } -
De-rendering the World's Revolutionary Artefacts
Shangzhe Wu, Ameesh Makadia, Jiajun Wu, Noah Snavely, Richard Tucker, Angjoo Kanazawa
CVPR 2021
Page
Video
Paper
Code
@InProceedings{wu2021derender, title = {De-rendering the World's Revolutionary Artefacts}, author = {Shangzhe Wu and Ameesh Makadia and Jiajun Wu and Noah Snavely and Richard Tucker and Angjoo Kanazawa}, booktitle = {CVPR}, year = {2021} } -
Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild
Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
CVPR 2020 (Best Paper Award), also in TPAMI 2021, IJCAI SCBP Track 2021
Page
Demo
Video
Paper
Paper (TPAMI)
Code
@InProceedings{wu2020unsup3d, title = {Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild}, author = {Shangzhe Wu and Christian Rupprecht and Andrea Vedaldi}, booktitle = {CVPR}, year = {2020} } -
Deep High Dynamic Range Imaging with Large Foreground Motions
Shangzhe Wu, Jiarui Xu, Yu-Wing Tai, Chi-Keung Tang
ECCV 2018
Page
Paper
Paper (High Res)
Sup Mat
Poster
Code
@InProceedings{wu2018hdr, title = {Deep High Dynamic Range Imaging with Large Foreground Motions}, author = {Shangzhe Wu and Jiarui Xu and Yu-Wing Tai and Chi-Keung Tang}, booktitle = {ECCV}, year = {2018} } -
Image Generation from Sketch Constraint Using Contextual GAN
Yongyi Lu, Shangzhe Wu, Yu-Wing Tai, Chi-Keung Tang
ECCV 2018
Page
Paper
@InProceedings{lu2018sketch, title = {Image Generation from Sketch Constraint Using Contextual GAN}, author = {Yongyi Lu and Shangzhe Wu and Yu-Wing Tai and Chi-Keung Tang}, booktitle = {ECCV}, year = {2018} }