Shinyoung Yi (이신영, 李神榮)

I am a PhD student at the Visual Computing Lab., part of the School of Computing at KAIST, where I work on computer graphics and vision. My PhD advisor is Min H. Kim.

I have n BS in Mathematical Science, Physics (dual major), and Computer Science (Minor) from KAIST.

Email  /  GitHub  /  Google Scholar

profile photo

Research

I'm interested in computer graphics and vision. Especially, physically-based rendering and mathematical foundation of computer graphics.

project image

Spin-Weighted Spherical Harmonics for Polarized Light Transport


Shinyoung Yi, Donggun Kim, Jiwoong Na, Xin Tong, Min H. Kim
SIGGRAPH (ACM Trans. Graph.), 2024
code / project page / paper /

A unified theory of spin-0 (scalar) and spin-2 spherical harmonics for a frequency domain analysis of polarized light transport.

project image

Modeling Surround-aware Contrast for HDR Displays


Shinyoung Yi, Daniel S. Jeon, Ana Serrano, Se-Yoon Jeong, Hui-Yong Kim, Diego Gutierrez, Min H. Kim
Computer Graphics Forum (CGF), 2022
code / project page / paper /

An experiment and model for a surround-aware contrast sensitivity. The journal version of a previous work.

project image

Differentiable Transient Rendering


Shinyoung Yi, Donggun Kim, Kiseok Choi, Adrian Jarabo, Diego Gutierrez, Min H. Kim
SIGGRAPH Asia (ACM Trans. Graph.), 2021
code / project page / paper /

The first differentiable transient rendering.

project image

Modeling Surround-aware Contrast Sensitivity


Shinyoung Yi, Daniel S. Jeon, Ana Serrano, Se-Yoon Jeong, Hui-Yong Kim, Diego Gutierrez, Min H. Kim
Eurographics Symposium on Rendering (EGSR), 2021
code / project page / paper /

An experiment and model for a surround-aware contrast sensitivity.

project image

Compact Snapshot Hyperspectral Imaging with Diffracted Rotation


Daniel S. Jeon, Seung-Hwan Baek, Shinyoung Yi, Qiang Fu, Xiong Dun, Wolfgang Heidrich, Min H. Kim
SIGGRAPH (ACM Trans. Graph.), 2019
project page / paper /

A compact single-shot hyperspectral imaging using a diffractive optical element (DoE). The DoE yields a spectrally-varying point spread function which provides a cue for compressive reconstruction.


Design and source code from Leonid Keselman's Jekyll fork of Jon Barron's website