Guying Lin

I'm a first year PhD student in the Computer Science Department at Carnegie Mellon University supervised by Prof. Minchen Li. Previously, I earned my M.Phil. from the University of Hong Kong, where I was supervised by Prof. Taku Komura and Prof. Wenping Wang. Prior to that, I obtained my B.Eng. (Hons) from Zhejiang University.

Email / CV / Scholar / Github

Research

I am interested in the intersection of computer graphics and computer vision.

	Patch-Grid: An Efficient and Feature-Preserving Neural Implicit Surface Representation Guying Lin, Lei Yang†, Congyi Zhang, Hao Pan, Yuhan Ping, Guodong Wei, Taku Komura, John Keyser, Wenping Wang†(: equal contribution; †: corresponding author) Provisionally accepted by TOG with revisions* arXiv A unified neural implicit representation that models complex shapes efficiently, preserves sharp features, and effectively models surfaces with open boundaries and thin geometric features.
	Surface Extraction from Neural Unsigned Distance Fields Congyi Zhang, Guying Lin, Lei Yang, Xin Li, Taku Komura, Scott Schaefer John Keyser, Wenping Wang(: equal contribution) ICCV*, 2023 project page / arXiv / code A robust and efficient method to extract a high-quality surface from neural unsigned distance functions (UDFs).
	On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encoding Guying Lin, Lei Yang, Yuan Liu, Congyi Zhang, Junhui Hou, Xiaogang Jin, Taku Komura, John Keyser, Wenping Wang (: equal contribution) Under minor revision of TVCG* arXiv Studying the optimal sampling problem in network training for modeling neural implicit surfaces, especially those with rich geometric details.
	ProLiF: Progressively-connected Light Field network for efficient view synthesis Peng Wang, Yuan Liu, Guying Lin, Jiatao Gu, Lingjie Liu, Taku Komura, Wenping Wang Computers & Graphics project page / arXiv / code A Progressively-connected Light Field network for the novel view synthesis of complex forward-facing scenes which is able to achieve significantly better rendering quality than the vanilla neural light fields and comparable results to NeRF-like rendering methods.
	Neural parametric surfaces for shape modeling Lei Yang, Yongqing Liang, Xin Li, Congyi Zhang, Guying Lin, Alla Sheffer, Scott Schaefer, John Keyser, Yuan Liu, Taku Komura, Wenping Wang arXiv, 2023 arXiv The first piecewise neural surface representation that allows coarse patch layouts of arbitrary n-sided surface patches to model complex surface geometries with high precision, offering greater flexibility over traditional parametric surface.

Miscellanea

In addition to my passion for computer graphics, I have a keen interest in journalism. During my undergraduate studies, I had the privilege of interning as a journalist at Qianjiang Evening News, one of the prominent news organizations in China. Throughout my tenure, I had the invaluable opportunity to publish more than 20 news articles under the guidance of the Chief Reporter.

Additionally, during my free time, I derive joy from sketching, creating colorful paintings, and practicing Chinese traditional calligraphy.

I also enjoy 3D art creation. Here are some projects I worked on during my undergraduate studies.

Character Modeling: Little Girl Waiting with Flowers
Related Tools Used: Zbrush

I utilize Zbrush for character design, modeling, and coloring, while also employing skeleton binding to manipulate her posture.

Post-apocalyptic Game Scene Design
Related Tools Used: Maya, Substance 3D Painter, Unreal Engine4 (group work)
Video

We started with sketching the post-apocalyptic game scene design, utilizing Maya for modeling, Substance 3D Painter for creating texture maps, and Unreal Engine 4 for terrain modeling and rendering.

Game Design: Night Walker
Related Tools Used: Unity, Maya, Substance 3D Painter (group work)

We designed and developed a game using the Unity framework. In this game, we started from scratch and accomplished a series of tasks, including scene construction, character modeling, character control, and animation implementation.

Last updated Dec. 2023. Template from Jon Barron.