Chenyang Qi

I am a third-year Ph.D. student at the Hong Kong University of Science and Technology (HKUST), supervised by Prof. Qifeng Chen.

In 2020, I received my Bachelor's Degree in Automation, Zhejiang University with a National Scholarship from Chu Kochen Honors College .

From June 2022 to December 2022, I worked as a research intern at MSRA, supervised by Bo Zhang , Dong Chen, and Fang Wen.

After that, I was fortunate to work at Tencent AI Lab with Xiaodong Cun , Yong Zhang, Xintao Wang and Ying Shan on project FateZero about video diffusion model

Currently, I am a student researcher at Google Research (Mountain View) and focusing on text-driven image & video enhancement.

我正在寻找2024年秋季入职的全职岗位, 欢迎邮件联系

I will graduate at 2024 Fall. Drop me an Email if your are recruting!

Email  /  CV  /  Google Scholar  /  Github

profile photo

  • News (July 2023): FateZero is accepted by ICCV 2023 as an Oral presentation.
  • News (July 2023): I gave a talk about FateZero at CVPR 2023 workshop.
  • News (Mar 2023): Excited to release the first zero-shot video editing framework FateZero using text-to-image diffusion models!
  • News (Feb 2023): Two papers are accepted by CVPR 2023! More details are coming.
  • News (June 2022): One paper is accepted to ACM Multimedia 2022.
  • News (Mar 2022): One paper is accepted to CVPR 2022.
Research

Currently, I am working on video generation and editing using AIGC techniques!
Hover your mouse over the image box below to view more results.
Left: input; Right: output

FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
Chenyang Qi, Xiaodong Cun , Yong Zhang,
Chenyang Lei, Xintao Wang , Ying Shan, Qifeng Chen
ICCV Oral, 2023
arxiv / code / project page

Editing your video via pretrained Stable Diffusion model without training.
(e.g., Replace the jeep with a posche car; Add Van Gogh style to the sunflower)
Real-time 6K Image Rescaling with Rate-distortion Optimization
Chenyang Qi,* Xin Yang*, Ka Leong Cheng, Ying-Cong Chen, Qifeng Chen
CVPR, 2023
arxiv / code

Image upscaling with learnable frequency-domain quantization to achieve 6K real-time speed and best rate-distortion.

MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
Bowen Zhang*, Chenyang Qi*, Pan Zhang, Bo Zhang,
HsiangTao Wu, Dong Chen, Qifeng Chen, Yong Wang, Fang Wen
CVPR, 2023
arxiv / code / project page

Identity-preserving talking head generation utilizing dense landmarks and
spatial-temporal enhancement with GAN priors.
(e.g., Make Marilyn Monroe speak as the motions of another person in the driving video)

Real-time Streaming Video Denoising with Bidirectional Buffers
Chenyang Qi*, Junming Chen*, Xin Yang, Qifeng Chen
ACM Multimedia, 2022
arxiv / code / project page

An extremely efficient (700X speedup) buffer-based framework for online video denoising.

Shape from Polarization for Complex Scenes in the Wild
Chenyang Lei*, Chenyang Qi*, Jiaxin Xie*, Na Fan, Vladlen Koltun , Qifeng Chen
CVPR, 2022
arxiv / code / project page

Scene-level normal estimation from a single polarization image using physics-based priors.

Experience
Student Researcher, Google Research, Mountain View
July, 2023 - Present
Research Intern, Tencent AI Lab, Shenzhen
Jan, 2023 - June, 2023
Research Intern, Microsoft Research Asia, Beijing
June, 2022 - December, 2022
Honors and Awards
  • National Scholarship, 2018 (Chu Kochen Honors College, Zhejiang University)

Thanks Dr. Jon Barron for sharing the source code of his personal page.