(Kenny) Chee Kim, Gan | 顏子鈞

I am an incoming Ph.D student in Electrical and Computer Engineering at the University of Southern California (USC). I currently serve as a research assistant at Academia Sinica, working with Dr. Jun-Cheng chen on topics related on Generative Video Processing/Restoration & World Model. I earned my B.S and M.S from National Taiwan Univeristy (NTU) in Electrical Engineering, and I was fortunate to worked with Prof. Jian-Jiun Ding on Image/Video Signal Processing.
Research Interests
My research interests span from low-level (image/video signal processing, computer vision) to high-level (computational imaging, generative AI) vision tasks.
Hobbies
I enjoy reading, coffee, hiking, basketball, watching animes when I am free.
Experiences
I gained valuable industry experiences at Novatek, MediaTek, and MobileDrive.
- Novatek (full-time): R&D AI-based and handcraft-based image/video signal processing algorithms for camera SoC. Modules designed includes HDR, noise reduction, motion detection.
- MediaTek (internship): Accelerate CNNs, working on codec standards like H.265/H.266 including deblocking filter.
- Mobiledrive (internship): Integrate multi-threaded software architecture for ADAS services, including Bird-Eye-View 3D Object Detection and Tracking.
Contact
- Email: gankenny26@gmail.com or kenny_gan@citi.sinica.edu.tw
- LinkedIn: LinkedIn
News
- (03/25/2026) I have been accepted to USC ECE Ph.D.
Publication
Exploiting Attention-to-Motion via Transformer for Versatile Video Frame Interpolation (GitHub)
Chee Kim Gan, Jian-Jiun Ding, Chang-Yu Hsieh, De-Yan Lu
ICASSP 2025
Adaptive face detection algorithm in blurring scenarios
Yi-Wei Tsai, Chee Kim Gan, Jian-Jiun Ding
IWAIT 2025
Article
A Tutorial for Diffusion Model in 2023
A comprehensive review of theory, architectures, applications, and video generation of the Diffusion Models (up to June 2023)
Last updated: 2026/03/29