Hanbyul Joo
Hanbyul Joo
Seoul National University · Computer Science and Engineering
Professor
Prof. 주한별
Professor's page · publicationsAbout
서울대학교 컴퓨터공학부 시각컴퓨팅 연구실(Visual Computing Lab)은 기계와 로봇이 인간처럼 세상을 보고 인간의 행동을 3차원으로 인지·이해하도록 하는 것을 목표로 한다. 컴퓨터 비전, 머신러닝, 컴퓨터 그래픽스의 교차점에서 인체 모션 캡처, 손-물체 상호작용, 인간-로봇 상호작용 등을 연구한다. 주한별 교수는 카네기멜런대학교(CMU) 로보틱스 연구소에서 박사학위를 받았으며, 페이스북 AI 리서치(FAIR) 연구원을 거쳐 서울대에 부임하였다.
Research keywords
Recent papers
- BUMP: Body-driven Unified Multi-object Physics for HOI SynthesisNewPreprintarXiv (Cornell University) · Oct 19
- RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot LearningPreprintarXiv (Cornell University) · Oct 7
- Co${}^{2}$Skill: Whole-Body Control via Skill Composition for Long-Horizon Human-Environment InteractionPreprintarXiv (Cornell University) · Oct 7
From OpenAlex · papers whose author affiliation matches this university
Selected publications
- ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object InteractionsCVPR · 2025
- PERSE: Personalized 3D Generative Avatars from A Single PortraitCVPR · 2025
- DAViD: Modeling Dynamic Affordance of 3D Objects using Pre-trained Video Diffusion ModelsICCV · 2025
- Learning to Generate Human-Human-Object Interactions from Textual DescriptionsNeurIPS · 2025
- Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion ModelsECCV · 2024
- Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted CameraCVPR · 2024
Labs doing related research
Labs that recently published on topics this lab's recent papers share
Shared topic: Robot Manipulation and Learning
Computer Vision Lab
POSTECH · Computer Science and Engineering
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress TestingNewPreprintarXiv (Cornell University) · Sep 29Visual AI Lab @ Yonsei
Yonsei University · Computer Science
IORA: Irregular Object Immobilization under Restricted ActuationNewPreprintarXiv (Cornell University) · Oct 22Su-Chul Lim
Dongguk University · Mechanical Engineering
VisForce: Visual Grounding of Current and Desired Forces for Goal-Conditioned Dexterous ManipulationPreprintarXiv (Cornell University) · Sep 22
Other labs in this department
- Gunhee KimRecruiting
Vision & Learning
- Taehyun KimRecruiting
Quantum Information & Computing
- KyoungSoo ParkRecruiting
Kyoungsoo Park
T-Networking
- Jaesik ParkRecruiting
Vision & Geometric Intelligence
- Jinwook SeoRecruiting
Human-Computer Interaction
- Yongsoo SongRecruiting
Cryptography & Privacy