Zhizhuo (Z) Zhou

I am a first year PhD student at Stanford University working on 3D generative AI. 

I was an MSR student at Carnegie Mellon University, where I am grateful to have worked with Shubham Tulsiani. I was also fortunate to work with David Fouhey during my undergrad at the University of Michigan. I am thankful to receive funding from NSF GRFP. 

X  |  Email  |  CV   |  Google Scholar  |  Blog  |  Github  


Apr 2024 - [MVD-Fusion] Single image to multi-view RGB-D in seconds at CVPR 2024!

Dec 2022 - [SparseFusion] Check out our latest work that unifies advances in neural rendering and image generation! 

Oct 2022 - [Talk] Won Meta-AI CO3D Challenge few-view reconstruction track at ECCV 2022 NGR-CO3D workshop! 

Jul 2022 - TA for AI4ALL@CMU 2022!

June 2021 - [Paper] Quantifying Bird Skeletons accepted at CV4Animals Workshop In conjunction with CVPR 2021!

Mar 2021 - Awarded NSF GRFP.

Jan 2021 - Won ProjectX ML research competition focused on climate change, advised by Sindhu Kutty. 

Mar 2020   - [Article] Michigan Alexa Prize team entered semi-finals.  


I am interested in understanding and generating 3D scenes from casual videos, images, and text. 

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation

Hanzhe Hu*, Zhizhuo Zhou*, Varun Jampani, Shubham Tulsiani

*Equal contribution

CVPR 2024

We propose a novel depth-aware 3D attention mechanism for generating multi-view consistent RGB-D images given a single RGB image. 

SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction

Zhizhuo Zhou, Shubham Tulsiani

CVPR 2023

We propose a 3D neural mode-seeking formulation that combines probabilistic generation of unseen regions with faithful reprojection of seen regions in a consistent 3D representation.

Quantifying Bird Skeletons

Zhizhuo Zhou, Gemmechu Hassena, Brian C. Weeks, David F. Fouhey

CV4Animals Workshop in conjunction with CVPR 2021

We can measure bird skeleton specimens extraordinarily accurately and quite fast with deep learning. This system can unlock datasets of birds at unprecedented scales.



Awards and Honors