About me/What I did 8

[Dataset 제작] Polygom2K2K 데이터셋 만들기 (구. 2K2K 데이터셋)

https://sanghunhan92.github.io/conference/2K2K/ High-fidelity 3D Human Digitization from Single 2K Resolution Images | Project PageAbstract High-quality 3D human body reconstruction requires high-fidelity and large-scale training data and appropriate network design that effectively exploits the high-resolution input images. To tackle these problems, we propose a simple yet effective 3sanghunhan9..

About me/What I did 2025.04.21

[AM-RADIO, RADIOv2.5] Feature space 짧은 분석

https://github.com/NVlabs/RADIO GitHub - NVlabs/RADIO: Official repository for "AM-RADIO: Reduce All Domains Into One"Official repository for "AM-RADIO: Reduce All Domains Into One" - NVlabs/RADIOgithub.com  궁극의 vision foundation model이 나온 것 같아서 직접 feature를 뽑아서 관찰해봤다. 결과 위 결과는 입력 이미지 6개를 전부 RADIOv2.5를 돌린 뒤, 다같이 PCA를 통해 3채널로 dimension reduction한 뒤 RGB로 mapping해서 시각화 한 결과다. 쉬운 말로 색깔이 비슷할 수록 해당 위치 ..

About me/What I did 2025.04.08

Github.io

github.io를 이용해 개인 웹사이트를 하나 만들었다. 소개 자료를 PPT나 PDF로 만들었더니 접근성이 아쉬워서 공개된 형태로 하나 제작했다. http://jseobyun.github.io jseobyun.github.io About me Hello, I’m Jongseob Yun. Thanks to visit this page! I’ve focused on computer vision and computer graphics that handle human stuffs(face, body pose/shape) and 3D geometric tasks (SfM, MVS, surface reconstruction, neural rendering). I am current jseobyun.github.io

About me/What I did 2023.10.01