Ph.D. in Computer Graphics, Johns Hopkins University
I'm currently working for Disney!
I'm currently working for Adobe!
I'm currently working for Apple!
I love computer graphics! I'm always ready to talk about tessellation, curvature, or surface reconstruction. Don't hesitate to reach out if you want to discuss these topics.
I earned a Ph.D. degree at Johns Hopkins University. In January 2024, my dissertation ``Feature Preserving Neural Surface Reconstruction Using the Dirichlet Energy of the Gauss Map" passed examination! Committee: Misha Kazhdan, Noam Aigerman, Noah Cowan.
I find myself lucky to work in the most exciting field, at the best jobs, with the most amazing colleagues in this world. Computer Graphics unites the disciplines of computing, mathematics, art, and physics, creating a captivating field of study. The dynamic nature of this intersection presents a plethora of exhilarating opportunities for exploration and discovery. One cannot think of more exciting things to investigate than this.
Teaching is about sharing the excitement and making the cool stuff accessible. Same reason why writing a paper or releasing a software. Therefore, I'm always developing an evolving version of graphics and geometry course. In the last semester at Hopkins, I served as a part-time teaching faculty. At this position, I taught my version of Intro to Graphics to Hopkins freshman students. I read papers on computer science education, as well as diversity and inclusion. My focus is advocating for a welcoming work atmosphere that supports underrepresented communities in computer science and engineering. I served the position of social chair of GRACE and offered mentorship through WiCS at Hopkins.
I enjoy coding. If going too many consecutive days not writing code, it starts to feel a bit strange. These are the cutest softwares I created so far. Working on more. The dream is to have my own C++ library.
• A small tool that measures how curved a surface is, working universally for triangle meshes and point clouds.
• A Swift api for arkit, released at WWDC 2022.
• I had the fortunate opportunity to be involved in this project during my time at Apple.
• An extensively streamlined Matlab implementation of PoissonRecon.
• Friendly for beginners, no octree, no any blackbox, implemented multigrid solver from scratch.
The cutest paper is always the next paper. Working on more.
ICCV, 2021
Yawei Li, Crane Chen, Zhaopeng Cui, Radu Timofte, Marc Pollefeys, Greg Chirikjian, Luc Van Gool
ECCV, 2020 (SPOTLIGHT)
Crane Chen, Pengfei Guo, Pengfei Li, Gim Hee Lee, Greg Chirikjian
Apart from research, I have a broader interest in problem-solving.
At Hopkins, it is typical for students to be assigned real-world issues as group projects. I spent a greater amount of time than most on enjoyable side projects.
Augmented Reality Suggestive Contours for Brain Surgery demo
• Developed two apps for Microsoft Hololens with Unity, which involved features including gesture control, voice control, and gaze tracking.
• Calculated suggestive contour of CAD models using OpenGL libraries. Applied the Vuforia marker to detect the 3D model position and overlay suggestive contours on a 3D printed model.
Occlusion R-CNN for Pedestrian Detection demo
• Appeared on the news at JHU.
• Provided a solution for occlusion situation in pedestrian detection.
UR5 Robot Arm Playing Piano demo
• Developed an app with MATLAB and ROS, which enables UR5 automatically read-understand-play any encoded music score (i.e. a data set encoding notes).