Name LI Chengze
Title Dr
Address Room A806
Telephone 3702 4221
School School of Computing and Information Sciences
Research Interest 2D Non-photorealistic Graphics, Computational
Photography, Image and Video Processing, and HCI


My name is Chengze Li, and I currently work as an Assistant Professor in the School of Computing and Information Sciences at Caritas Institute of Higher Education. I received my B.Eng. degree from University of Science and Technology of China in 2013, and Ph.D. degree from Department of Computer Science and Engineering, the Chinese University of Hong Kong in 2020.

In recent years, my research focuses on the understanding and processing of 2D non-photorealistic contents with deep learning techniques. Especially, I wrote several papers on the processing of ACG (animation, comics, games) contents and some of them are accepted by top venues such as ACM SIGGRAPH. I am also interested in some other computer vision and graphics topics, such as computational photography, deep image semantic understanding, visualization, and human-computer interaction.

I write production codes for my research projects, and some of them are available on the internet. Besides, I also know some frontend programming—one of my favourite works is the frontend design of the USTC Open Source Mirror.


Before I joined CIHE, I worked as course tutors and was responsible for the tutorial sessions, course practices, homework, and examinations of multiple courses in CUHK, including:

 I also worked as an (Acting) Postdoctoral Fellow in the CUHK Jockey Club AI for the Future Project, which aims at promoting AI education to middle school students and teachers. In this project, I was responsible for the course design of AI curriculums. I also designed a set of corresponding AI laboratory sessions and materials in software and hardware platforms for the project.


My research interests include 2D non-photorealistic graphics, computational photography, image and video processing, and HCI. In recent years, I worked together with my colleges and the ACG (2-dimensional media) community to research real-life challenges in the production of comics, illustrations, and animations. Meanwhile, we also developed various applications towards user-friendly and efficient processing in the comics and animation pipeline to save the production cost.

I am currently a professional member of ACM. I also help with peer-reviewing in several conference events and journals, including ACM SIGGRAPH, IEEE TVCG, IEEE TPAMI, etc.

Selected Publications

Xueting Liu, Chengze Li, Haichao Zhu, Tien-Tsin Wong, Xuemiao Xu: Text-aware balloon extraction from manga. Vis. Comput. 32(4): 501-511 (2016)

Chengze Li, Xueting Liu, Tien-Tsin Wong: Deep extraction of manga structural lines. ACM Trans. Graph. 36(4): 117:1-117:12 (2017)

Lvmin Zhang*, Chengze Li*, Tien-Tsin Wong, Yi Ji, Chunping Liu: Two-stage sketch colorization. ACM Trans. Graph. 37(6): 261:1-261:14 (2018

Yi Guo, Zhuming Zhang, Chu Han, Wenbo Hu, Chengze Li, Tien-Tsin Wong: Deep Line Drawing Vectorization via Line Subdivision and Topology Reconstruction. Comput. Graph. Forum 38(7): 81-90 (2019)                           

Minshan Xie*, Chengze Li*, Xueting Liu, Tien-Tsin Wong: Manga filling style conversion with screentone variational autoencoder. ACM Trans. Graph. 39(6): 226:1-226:15 (2020)


For more information, please refer to the Google Scholar page.