Jae Won Jang

I am an integrated MS/PhD student at Artificial Intelligence from the College of Engineering in Seoul National University, where I was advised by Prof. Nojun Kwak in the Machine Intelligence and Pattern Analysis Lab (MIPAL). Previously, I obtained my bachelor's degree from the College of Engineering, SNU, majoring in Naval Architecture and Ocean Engineering and Industrial Engineering.

My research interests lie in 4D representation with Gaussian Splatting and Video Diffusion Model. Much of my recent work has focused on dynamic scene reconstrucition with Gaussian Splatting.

Email  /  CV  /  Google Scholar  /  X  /  Github

We present 4DGS360, a method for reconstructing 360° Gaussian representations of dynamic objects from a single monocular video.

We propose DivCon-NeRF, a novel ray augmentation method designed for few-shot novel view synthesis. By introducing surface-sphere and inner-sphere augmentation techniques, our method effectively balances ray diversity and geometric consistency, which helps suppress floaters and appearance artifacts often seen in sparse-input settings.

Thanks for sharing the website template, Jon Barron. :)