Shengqu Cai 蔡盛曲
I am a CS PhD student at Stanford University and a research scientist intern at Adobe Research.
My research is partly supported by a Stanford School of Engineering Fellowship.
Previously, I was a CS master student at ETH Zürich
supervised by Prof. Luc Van Gool.
In 2022, I spent a wonderful half a year visiting Stanford University at the Computational Imaging Lab led by Prof. Gordon Wetzstein, working on scene extrapolation with Eric Chan.
Before this, I obtained my Bachelor degree in Computer Science with first honour from King's College London in United Kingdom, working on unsupervised learning.
I am interested in solving graphics or inverse graphics tasks that are fundamentally ill-posed via traditional methods, slay the unslayable.
I have been working primarily around neural rendering, including but not limited to
generative models, inverse rendering, unsupervised learning, GAN inversion,
scene representations, visual content creation, etc.
Email  / 
CV  / 
Google Scholar  / 
Semantic Scholar  / 
Github  / 
Twitter  / 
Linkedin
|
|
News
2023-07: DiffDreamer is accepted by ICCV 2023, looking forward to Paris!
2023-02: I am admitted to Stanford University for PhD in Computer Science!
2023-01: I will be working as a research scientist intern at Adobe Research this summer!
2022-03: Pix2NeRF is accepted by CVPR 2022. First submission first accept!
2022-03: Started my master thesis at Stanford University. Looking forward to visiting bay area!
|
Publications
* indicates equal contribution
|
|
DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models
Shengqu Cai,
Eric Ryan Chan,
Songyou Peng,
Mohamad Shahbazi,
Anton Obukhov,
Luc Van Gool,
Gordon Wetzstein
In ICCV, 2023
[Project Page][Paper][Code]
A diffusion-model based unsupervised framework capable of synthesizing novel views depicting a long camera trajectory flying into an input image.
|
|
Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translation
Shengqu Cai,
Anton Obukhov,
Dengxin Dai,
Luc Van Gool
In CVPR, 2022
[Paper][Code]
3D-free unsupervised Single view NeRF-based novel view synthesis via conditional NeRF-GAN training and inversion.
|
Misc
Conference Review: CVPR, ICCV, NeurIPS
Journal Review: IJCV, Computing Surveys
|
© Shengqu Cai | Last updated: July 14, 2023 | Website Template
|