Zicong Jiang

Hello! I am the first-year PhD student at Communication Systems Group, Chalmers University of Technology, Sweden, supervised by Assist. Prof. Christian Häger, Prof. Erik Agrell (IEEE Fellow), and Prof. Magnus Karlsson (IEEE Fellow). I just finished my master thesis at IVRL, EPFL, under the guidance of Prof. Sabine Süsstrunk, Yufan Ren and Prof. Søren Forchhammer, I work on 2D/3D contents generation, AIGC, and Diffusion Models.

Prior to my PhD study, I earned my master's degree from Technical University of Denmark, Denmark. I earned my bachelor's degree from Northeast Electric Power University, Jilin. Those four years were some of the happiest of my life.

I'm passionate about utilizing AI methods to fix the problem in communication systems (Specifically in joint optical fiber sensing and communication systems) and the implementation of algorithms in real world via FPGA, I am also interested in the recent advancement in generative models (Diffusion Models) and it's application in 3D/2D generation and editing, and I'm always eager to engage in discussions on these topics.

For master and bachelor students who interested in AI and it's applications, I am looking for thesis students, the avaliable topics are listed here. You can contact me via email zicongj(AT)chalmers.se (change (AT) as @).

Email  /  Google Scholar  /  LinkedIn  /  GitHub

👏 [Nov, 2024]: I start my PhD study at Chalmers University of Technology, Sweden, supervised by Assist. Prof. Christian Häger, Prof. Erik Agrell (IEEE Fellow), and Prof. Magnus Karlsson (IEEE Fellow).

🎉 [Jul, 2024]: The next International Conference on Computational Photography (ICCP) is happening at EPFL, Switzerland in 2024. I am excited to announce my role as a student volunteer.

🎓 [Jul, 2024]: I successfully defended my master thesis on Prompt-guided mesh texurization at EPFL, Switzerland.

This is part of my undergraduate thesis project. It is an improved version based on YOLOv4-tiny, which implements an object detection algorithm capable of running in real-time on embedded devices such as Raspberry Pi.

This is part of my undergraduate thesis project. We designed a head-mounted smart glasses device for circuit inspection based on Raspberry Pi. We used STUN technology to achieve NAT traversal for remote data transmission. The system includes a management terminal and a head-mounted display terminal, capable of real-time audio and video calls, text and image transmission and storage, voice control, and real-time insulator defect fault detection.

We research text-guided 3D generation and propose a novel algorithm that supports using a single normal map or mesh as input. This algorithm utilizes neural networks to generate multiple view-consistent color maps and normal maps. Leveraging this information, we can swiftly accomplish mesh generation and coloring in under a minute. Moreover, our method effectively resolves the significant issue of multiview inconsistency that has been persistent in previous works.

The project will review the state of the art on linear and nonlinear predistortion applied to optical transmitters, as well as implement a few of the simple common methods. The project will also investigate the use of ML tools for the compensation (pre- and/or post) of linear and nonlinear signal distortion caused by practical limitations of components employed in optical communication systems.