Publications

I am fortunate to collaborate with talented students and researchers around the world on multimodal generative models for image and video synthesis. See Google Scholar for the complete list. (* equal contribution)

Generative Manifold Distillation teaser
Generative Manifold Distillation: Aligning Restoration Trajectories with Natural Image Prior
Yuyang Hu, Mojtaba Sahraee-Ardakan, Arpit Bansal, Kangfu Mei, Chenyang Qi, Peyman Milanfar, Mauricio Delbracio
ECCV 2026
PDF
Instruction-based image editing results Instruction-based image editing framework
Instruction-based Image Editing with Planning, Reasoning, and Generation
Liya Ji, Chenyang Qi, Qifeng Chen
CVPR 2025
PDF
SPIRE teaser
SPIRE: Semantic Prompt-Driven Image Restoration
Chenyang Qi, Zhengzhong Tu, Keren Ye, Mauricio Delbracio, Peyman Milanfar, Qifeng Chen, Hossein Talebi
ECCV 2024
Project Page
Work done during my internship at Google Research.
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 2023 · Oral
arXiv Code Project Page GitHub stars
Edit your video with a pretrained Stable Diffusion model — no training required (e.g., replace a jeep with a Porsche, or restyle sunflowers à la Van Gogh).
Follow-Your-Click teaser
Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts
Yue Ma*, Yingqing He*, Hongfa Wang, Andong Wang, Chenyang Qi, Chengfei Cai, Xiu Li, Zhifeng Li, Heung-Yeung Shum, Wei Liu, Qifeng Chen
arXiv 2024
arXiv Code Project Page GitHub stars
AnimateZero teaser
AnimateZero: Video Diffusion Models are Zero-Shot Image Animators
Jiwen Yu, Xiaodong Cun, Chenyang Qi, Yong Zhang, Xintao Wang, Ying Shan, Jian Zhang
arXiv 2023
arXiv Code Project Page GitHub stars
MagicStick teaser
MagicStick: Controllable Video Editing via Control Handle Transformations
Yue Ma, Xiaodong Cun, Yingqing He, Chenyang Qi, Xintao Wang, Ying Shan, Xiu Li, Qifeng Chen
arXiv 2023
arXiv Code Project Page GitHub stars
Celeb Basis teaser
Inserting Anybody in Diffusion Models via Celeb Basis
Ge Yuan, Xiaodong Cun, Yong Zhang, Maomao Li, Chenyang Qi, Xintao Wang, Ying Shan, Huicheng Zheng
NeurIPS 2023
Project Page Code
Face identity customization in diffusion models.
HyperThumbnail framework HyperThumbnail rate-distortion curve
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
Learnable frequency-domain quantization for 6K real-time image rescaling with the best rate-distortion trade-off.
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 with dense landmarks and spatial-temporal enhancement.
Real-time Streaming Video Denoising with Bidirectional Buffers
Chenyang Qi*, Junming Chen*, Xin Yang, Qifeng Chen
ACM MM 2022
arXiv Code Project Page
An extremely efficient (700× speedup) buffer-based framework for online video denoising.
Shape from Polarization results Shape from Polarization framework
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.