|
I am a graduate student at Seoul National University. I am advised by Professor Nojun Kwak, as a member of Machine Intelligence and Pattern Analysis Lab (MIPAL). Prior to my graduate studies, I earned a bachelor's degree in Astronomy and Industrial Engineering.
Email / CV / Google Scholar / Github |
|
|
|
 
|
Seunghyeon Seo, Yeonjin Chang, Jayeon Yoo, Seungwoo Lee, Hojun Lee, Nojun Kwak We cast an hourglass as an additional training ray, which adaptively regularizes the high-frequency components of the samples, and enhance the integrity of training framework by conceptualizing the hourglass as a bundle of flipped diffuse reflection rays, aligning with the Lambertian assumption. |
 
|
Yeonjin Chang, Yearim Kim, Seunghyeon Seo, Jung Yi, Nojun Kwak WACV, 2024 arXiv We simplify outdoor scene relighting for NeRF by aligning with the sun, eliminating the need for environment maps and speeding up the process using a novel cubemap concept within the framework of TensoRF. |
|
Seunghyeon Seo, Yeonjin Chang, Nojun Kwak ICCV, 2023 project page / arXiv We utilize the flipped reflection rays as additional training resources for the few-shot novel view synthesis, leading to more accurate surface normal estimation. |
 
|
Seunghyeon Seo, Donghoon Han*, Yeonjin Chang*, Nojun Kwak CVPR, 2023 project page / arXiv We model a ray with mixture density model, leading to efficient learning of density distribution with sparse inputs, and propose an effective auxiliary task of ray depth estimation for few-shot novel view synthesis. |
 
|
Jookyung Song, Yeonjin Chang*, Seonguk Park, Nojun Kwak ICASSP, 2023 arXiv Write short description here. |