Shengqu Cai 「蔡盛曲」

I'm a second-year CS PhD student at Stanford University, advised by Prof. Gordon Wetzstein and Prof. Leonidas Guibas, affliated with Computational Imaging Lab and Geometric Computing Lab. I am partly supported by a Stanford School of Engineering Fellowship.

Before Stanford, I was a CS master student at ETH Zürich supervised by Prof. Luc Van Gool. I obtained my Bachelor degree in Computer Science with first honour from King's College London in United Kingdom, where I spent some time working on information theory.

In 2022, I spent a few wonderful months working on diffusion with Eric Chan and Songyou Peng. I started my research career back in 2021 working on NeRFs and GANs with Anton Obukhov. I consider them as mentors coming into research and who I try to learn from.

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 and generative models, including but not limited to diffusion models, inverse rendering, unsupervised learning methods, scene representations, etc. I like making cool theories, videos, demos and applications.

Email  /  CV  /  Google Scholar  /  Semantic Scholar  /  Github  /  Twitter  /  Linkedin

• 2024-09: CVD is accepted to NeurIPS 2024, see you in Vancouver!
• 2024-02: Generative Rendering is accepted to CVPR 2024, see you in Seattle!
• 2023-09: I joined Stanford University for PhD in Computer Science!
• 2023-07: DiffDreamer is accepted by ICCV 2023, looking forward to Paris!
• 2023-05: I graduated from ETH Zürich!
• 2023-01: I will be working as a research intern at Adobe this summer!
• 2022-03: Pix2NeRF is accepted by CVPR 2022. First submission first accept!

* indicates equal contribution

Training-free customized image generation model that scales to any instance and any context.

Multi-view/multi-trajectory generation of videos sharing the same underlying content and dynamics.

Render low fidelity animated mesh directly into animation using pre-trained 2D diffusion models, without the need of any further training/distillation.

Render low fidelity animated mesh directly into animation using pre-trained 2D diffusion models, without the need of any further training/distillation.

A diffusion-model based unsupervised framework capable of synthesizing novel views depicting a long camera trajectory flying into an input image.

3D-free unsupervised Single view NeRF-based novel view synthesis via conditional NeRF-GAN training and inversion.