Zihao Ye

Hi, I am Zihao Ye (叶子皓), which means “Luminous Leaf” in the cultural context of China. I am currently an M.Sc. student in the Artificial Intelligence Engineering - Information Security program at Carnegie Mellon University.

My current research interests are representation learning theory and application. My previous experience can be found in my bio.

I obtained my B.Sc. through a joint program between Queen Mary University of London and Beijing University of Posts and Telecommunications, and I worked with Prof. Changjae Oh, in 2023.

In addition to my academic pursuits, I am also passionate about music. I play guitar 🎸 and sing.

news

Jun 7, 2024	A paper on reference-guided image filtering (de-raining) was accepted to ICIP 2024! 🎉✨

selected publications

2024

ICIP

Improving Image de-raining Models using Reference-guided Transformers

Zihao Ye, Jaehoon Cho, and Changjae Oh

IEEE International Conference on Image Processing, 2024

ABSTRACT arXiv PDF Blog Code Poster

Image de-raining is a critical task in computer vision to improve visibility and enhance the robustness of outdoor vision systems. While recent advances in de-raining meth- ods have achieved remarkable performance, the challenge remains to produce high-quality and visually pleasing de- rained results. In this paper, we present a reference-guided de-raining filter, a transformer network that enhances de- raining results using a reference clean image as guidance. We leverage the capabilities of the proposed module to further refine the images de-rained by existing methods. We vali- date our method on three datasets and show that our module can improve the performance of existing prior-based, CNN- based, and transformer-based approaches.