3D Computer Vision / Pose and Mesh Reconstruction
I am a combined MS/PhD student at the Artificial Intelligence Graduate School (AIGS), UNIST, and a member of the UNIST Vision and Learning Lab (UVLL), advised by Prof. Seungryul Baek. I received my B.S. degree in Statistics from Chonnam National University.
My research focuses on 3D human and hand-object reconstruction from monocular videos, with broader interests in multi-person tracking, 3D computer vision, and human-object interaction.
M.S./Ph.D., AIGS, UNIST Sep. 2024 - Current
I will visit the University of Oxford as a Visiting Researcher from September to December 2026.
(Little updates from Oxford: come peek at my diary! )
Our paper "Multi-THuMBS: Multi-person Tracking of 3D Human Meshes Beyond Video Shots" has been accepted to .
Our paper "BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting" has been accepted to .
Won 1st place at the HANDS Workshop Challenge, ARCTIC Track.
Won 3rd place at the HANDS Workshop Challenge, Consistent Motion Reconstruction.
교수님 면담, 연구실 출근, 크라이스트 처치 방문.
학생증 발급, 자전거 구매, 도서관 구경, 집 계약.
상하이 관광, 영국 입국, 옥스포드 이동.
PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interaction...
InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds (arXiv, 2024)
Can Generative Video Models Help Pose Estimation? (Inter-pose)
D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Recon...
HORSE: 3D Reconstruction of Objects in Hands without Real World 3D Supervision