Yaoyi (Elyson) Bai
Computer Graphics
PROJECTS
I'm interested in rendering, especially appearance. I am also interested in Physically Based Material Simulation, Augmented Reality, and computer graphics-related topics. My recent projects are listed here. Also, my Github will provide more information about my projects.
Latest Projects
Neural Complex Luminaires: Representation and Rendering
Zhu J, Bai Y, Xu Z, Bako S, Velázquez-Armendáriz E, Wang L, Sen P, Hašan M, Yan LQ. Neural complex luminaires: representation and rendering. ACM Transactions on Graphics (TOG). 2021 Jul 19;40(4):1-2.
ACM Transactions on Graphics (Proceedings of SIGGRAPH 2021)
Step into the Bubble: A Novel, Augmented Reality (AR) User Interface
Can we place the love status on campus in random places? Augmented Reality will not only allow the status to be placed on any location but revise their sizes, and colors and people can play with the letters. Or perhaps people do not want Ben Franklin on a bench, they prefer him reading the newspaper at a kitchen table and a cup of coffee. Augmented Reality is capable of providing various kinds of tables for people to choose from. And people's novel designs can be shared with the publish. Join us and enjoy the virtual world.
Advisor: Dr. Stephen H Lane
ACM SIGGRAPH 2020 Appy Hour, 1-1
Master's Thesis: Complex Luminaire Rendering Technique Studies
Rendering complex luminaires such as chandeliers have been time-consuming and inefficient if implemented through traditional physically based rendering algorithms. Their detailed features cannot be properly described by traditional means. A more practical way is to separate rendering into two stages, so that precomputed data can be reused. In this paper, we propose a novel method based on Vel ́azquez-Armend ́ariz et al.’s work.
Results are tested and rendered through various types of scenes and luminaires, and the
rendering times are recorded. The results indicate that our method can produce smooth
results with luminaire appearance and illumination details with fewer samples per pixel, and
considerably less time, than multiple importance sampling the full lighting integrator. Our
method is capable of rendering visibly accurate results for complicated luminaire geometries.
Advisor: Dr. Normal Badler
Simulating Elastic Materials with MPM Solver
This project is modeling elastic materials both in freefall and collision using a Material Point Method (MPM) solver.
Advisor: Dr. Chenfanfu Jiang, Dr. Andre Pradhana
Collaborators: Joshuah Wolper, Ziyin Qu
Cesium Snow Rendering
Cesium has a great Terrain system that is capable of displaying accurate shapes of mountains and glaciers. Cesium displays high or steep terrains with perspective, allowing the user to physically see mountain heights and shadows. Before, snow is added as a texture, which has limitations: the texture modifies a preexisting scene to make it snow-covered and offers no depth information. We implemented the add-in real-time snow on the terrain would make the system more realistic. Our project also enabled snow accumulation in real-time through Perlin noise. Generally, we focused on rendering snow with the idea of creating a framework to incorporate the future other weather-related changes in real-time.
Collaborators: Yuxin Hu, Dr. Anton Khabbaz
Magic Offspring Maya Plugin
This project implemented a shape blending Maya plugin based on the paper Topology-Varying 3D Shape Creation via Structural Blending written by Alhashim, I. Magical Offspring is a tool for fast generation of novel shapes by blending a source and target shape of the same object category, but with different topological and geometric structure. It helps game developers generate many objects like furniture, robotics, and airplanes with variant shapes that are usually needed in games, without requiring developers to manually model every shape themselves.
Collaborator: Yuxin Hu