Jin-Hyeong Park

Research Engineer at Neowiz,
M.S at Chung-Ang University in Korean.

About

I work on learning-based visual representations with an emphasis on physical structure and controllability. My interest lies in how neural models can be guided by physically meaningful priors—such as geometry, materials, and intrinsic image structure—to support reliable reconstruction, rendering, and editing of visual content.

I am currently a Research Engineer at Neowiz, where I have built deployable AI systems for game content creation and collaborated closely with artists in real production pipelines. These experiences shifted my focus from purely metric-driven modeling toward representations that can be controlled, trusted, and integrated into real workflows.

My research interests lie in Learning-based Inverse Rendering, Neural Scene Representations, Controllable 3D Reconstruction and Editing.

Professional Experience

AI Research Institute, Neowiz
Research EngineerDec 2020 - Present

Machine Intelligence Lab, CAU
Research AssistantMar 2018 - Aug 2020
Research InternJul 2017 - Feb 2018

Publications

Published in SCI(E) Journals

Multi-label Naïve Bayes Classifier Considering Label Dependence
Hae Cheon Kim, Jin-Hyeong Park, Dae Won Kim, Jaesung Lee
Pattern Recognition Letters, Vol. 136(1), pp. 279-285, 1 August 2020
[paper]

Compact Feature Subset Based Multi-label Music Categorization for Mobile Devices
Jaesung Lee, Wangduk Seo, Jin-Hyeong Park, Dae Won Kim
Multimedia Tools and Applications, Vol. 78, pp. 4869-4883, 11 May 2018
[paper]

International Conference Papers

Multi Population Memetic Search for Effective Multi-label Feature Selection
Jin-Hyeong Park, Jaesung Lee
Platform Technology and Service, Jeju, Korea, 28-30 January 2019