Chia-Kai (Kai) Yeh

I obtained my PhD in Computer Science from Computational Photography Lab at Northwestern University , advised by Prof. Oliver Cossairt. I work on portable 3D Modeling and Appearance Acquisition system. I am now a Research Engineer at 8i Inc., working on volumetric video capturing.

Before 8i, I was the applied science lead at M^3, a tech startup empowering 3D modeling and understanding for social good. At M^3, I led the team to push the CV/CG research and development effort with 3D reconstruction with depth sensor or single RGB image and automatic 3D deformation algorithm for custom-fitted respirator design. Also, I led the team to develop a 3D selfie facial sizer. This is a 3D facial measurement technology that used only single RGB image with ML to measure true spatial dimentions with 1cm of margin of error.

I received my Bachelor’s degree at Electronics Engineering from Chang Gung University in Taiwan. Before attending Northwestern University, I worked as a camera designed engineer at 3D Aperture Technologies, an advanced camera module development company based in Taiwan. I participated in the projects that worked with clients such as Google ATAP and Amazon Lab126 on advance array camera module development(from evaluating and designing the optical mechanical system, camera sensor porting on embedded and Android platform to camera calibration procedure and image quality evaluation) and manufacturing. Also, I led the team designed and built tailor-made camera modules and entire multi-view capture system for the human body scanning studio to perform very high resolution of human body 3D mesh.

In 2016, I spent my summer as the visiting researcher in Graphics Labs at University of Southern California Institution of Creative Technologies with Dr. Andrew Jones and Prof. Paul Debevec to work on markerless performance capture and appearance modeling of humans.

In 2018 summer, I worked at Adobe Research as a Research Intern with Dr. Sunil Hadap and Dr. Duygu Ceylan for facial geometry and appearance modeling. Within the project, me and the team built up an icosahedron multi-view capture light dome for photorealistic human facial geometry and appearance modeling. We had took our project to showcase at 2019 Adobe Tech summit at San Francisco which we had captured nearly 500 faces on scene to create a high quality 3D human facial dataset.

Email / GitHub / LinkedIn / CV

Research

I'm interested in computational photography, computer graphics, computer vision, 3D reconstruction and appearance modeling.

	Diagnosing a Paint Disease with Computer Science: The Case of Georgia O’Keeffe Chia-Kai Yeh, Vikas Gupta, Florian Willomitzer, Dale Kronkright, Aggelos Katsaggelos, Marc Walton, Oliver Cossairt American Association for the Advancement of Science Annual Meeting, 2019 Video / Media Coverage / We create a novel hand-held metrology tool detects, maps and monitors destructive micron-sized protrusions resulting from a chemical reaction between the metal ions and fatty acids commonly used as binder in paints in precious works of art. Our system utilize only of a mobile hand held device such as tablets and mobile phone and exploits screen and front camera for Deflectometry-based surface measurements. We demonstrate high quality measurements without the need for an offline calibration procedure. This new tool will help conservators easily and effortlessly map and monitor the strange paint disease and prolong the lives of art.
	PhotoGeode: 3D Faces from 2D Imagery Chia-Kai Yeh, TJ Rodes, Bhautik Joshi, Duygu Ceylan, Sunil Hadap Adobe TechSummit, 2019 Video / Media Coverage / We create an icosahedron multi-view capture enviroment for photorealistic human facial geometry and appearance modeling. We had took our project to showcase at 2019 Adobe Tech summit at San Francisco which we had captured nearly 500 faces on scene and created a high quality 3D and appearance human facial dataset.
	CS-ToF: High-resolution compressive time-of-flight imaging Fengqiang Li, Huaijin Chen, Adithya Pediredla, Chia-Kai Yeh, Kuan He, Ashok Veeraraghavan, Oliver Cossairt OSA Optics Express, 2018 Paper / Use compressive sensing to improve the lateral resolution of the off-the-shelf ToF cameras.
	Shape-from-Shifting: Uncalibrated Photometric Stereo with a Mobile Device Chia-Kai Yeh, Fengqiang Li, Gianluca Pastorelli, Marc Walton, Aggelos K. Katsaggelos, Oliver Cossairt IEEE International Conference on eScience, 2017 Project Website / Paper / A mobile device approach for surface normal and shape recovery in the wild.
	A Streamlined Photometric Stereo Framework for Cultural Heritage Chia-Kai Yeh, Nathan Matsuda, Xiang Huang, Fengqiang Li, Marc Walton, Oliver Cossairt ECCV Workshop, 2016 Project Website / Paper / A streamlined framework of robust 3D acquisition for cultural heritage using both photometric stereo and photogrammetric information.