HJ
Hanbyul Joo
cs.CVcs.GRcs.ROcs.AIcs.LGVideo RecordingActivities of Daily Livingcs.SDDatabases, FactualImage Processing, Computer-Assisted
On Valency
published · living versionsW_cy2bmu9n·v1 · currentpublished
Learning the 4D World through Point Trajectory Forecasting
with Byungwoo Jeon, Sunghwan Hong, Dohyeon Kim, Jonghoon Lee +8
1 version
Preprints & journals
50 papers in the corpus · 2016–2026Learning the 4D World through Point Trajectory Forecasting2610.28594v1 · Byungwoo Jeon, Sunghwan Hong, Dohyeon Kim et al.2026 · 0 citationsarXivon Valency
BUMP: Body-driven Unified Multi-object Physics for HOI Synthesis2610.27066v1 · Wonjung Woo, Hyeonwoo Kim, Hanbyul Joo2026 · 0 citationsarXiv
CoSkill: Whole-Body Control via Skill Composition for Long-Horizon Human-Environment Interaction2610.09291v2 · Jeonghwan Kim, Hyeonwoo Kim, Hanbyul Joo2026 · 0 citationsarXiv
RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning2610.09455v1 · Seungjun Moon, Subin Jeon, Sangwoo Kim et al.2026 · 0 citationsarXiv
ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning2606.19340v3 · Jisoo Kim, Sangwon Baik, Taeksoo Kim et al.2026 · 0 citationsarXiv
DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation2604.20841v2 · Hyeonwoo Kim, Jeonghwan Kim, Kyungwon Cho et al.2026 · 0 citationsarXiv
HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments2604.14944v3 · Jongbin Lim, Taeyun Ha, Seongho Cha et al.2026 · 0 citationsarXiv
Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents2604.09781v2 · Sangwon Baik, Gunhee Kim, Mingi Choi et al.2026 · 0 citationsarXiv
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision2604.04934v2 · Hyunsoo Cha, Wonjung Woo, Byungjun Kim et al.2026 · 0 citationsarXiv
OmniEgoCap: Device-Agnostic Sequence-Level Egocentric Motion Reconstruction2512.19283v3 · Kyungwon Cho, Jeonghyeon Na, Hanbyul Joo2025 · 0 citationsarXiv
Dexterous World Models2512.17907v1 · Byungjun Kim, Taeksoo Kim, Junyoung Lee et al.2025 · 0 citationsarXiv
Ego4D: Around the World in 3,600 Hours of Egocentric Video.39058617 · Grauman, Kristen, Westbury, Andrew, Byrne, Eugene et al.2025 · 16 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(11):9468-9509
Audio Driven Real-Time Facial Animation for Social Telepresence2510.01176v2 · Jiye Lee, Chenghui Li, Linh Tran et al.2025 · 1 citationarXiv
Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer2509.04434v3 · Hyunsoo Cha, Byungjun Kim, Hanbyul Joo2025 · 0 citationsarXiv
HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars2507.19481v1 · Byungjun Kim, Shunsuke Saito, Giljoo Nam et al.2025 · 2 citationsarXiv
Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models2503.19914v2 · Sangwon Baik, Hyeonwoo Kim, Hanbyul Joo2025 · 0 citationsarXiv
DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models2501.08333v3 · Hyeonwoo Kim, Sangwon Baik, Hanbyul Joo2025 · 3 citationsarXiv
Learning to Transfer Human Hand Skills for Robot Manipulations2501.04169v1 · Sungjae Park, Seungho Lee, Mingi Choi et al.2025 · 0 citationsarXiv
PERSE: Personalized 3D Generative Avatars from A Single Portrait2412.21206v2 · Hyunsoo Cha, Inhee Lee, Hanbyul Joo2024 · 9 citationsarXiv
Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses2404.14410v1 · Inhee Lee, Byungjun Kim, Hanbyul Joo2024 · 12 citationsarXiv
PEGASUS: Personalized Generative 3D Avatars with Composable Attributes2402.10636v2 · Hyunsoo Cha, Byungjun Kim, Hanbyul Joo2024 · 7 citationsarXiv
Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models2401.12978v3 · Hyeonwoo Kim, Sookwan Han, Patrick Kwon et al.2024 · 5 citationsarXiv
GALA: Generating Animatable Layered Assets from a Single Scan2401.12979v1 · Taeksoo Kim, Byungjun Kim, Shunsuke Saito et al.2024 · 20 citationsarXiv
ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions2401.10232v2 · Jeonghwan Kim, Jisoo Kim, Jeonghyeon Na et al.2024 · 12 citationsarXiv
Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera2401.00847v2 · Jiye Lee, Hanbyul Joo2024 · 22 citationsarXiv
CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images2308.12288v2 · Sookwan Han, Hanbyul Joo2023 · 6 citationsarXiv
NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects2305.14345v2 · Taeksoo Kim, Shunsuke Saito, Hanbyul Joo2023 · 9 citationsarXiv
Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models2305.11870v3 · Byungjun Kim, Patrick Kwon, Kwangho Lee et al.2023 · 24 citationsarXiv
Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments2301.02667v2 · Jiye Lee, Hanbyul Joo2023 · 25 citationsarXiv
Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion2204.08451v1 · Evonne Ng, Hanbyul Joo, Liwen Hu et al.2022 · 99 citationsarXiv
BANMo: Building Animatable 3D Neural Models from Many Casual Videos2112.12761v3 · Gengshan Yang, Minh Vo, Natalia Neverova et al.2021 · 127 citationsarXiv
Modeling human intention inference in continuous 3D domains by inverse planning and body kinematics2112.00903v1 · Yingdong Qian, Marta Kryven, Tao Gao et al.2021 · 1 citationarXiv
Ego4D: Around the World in 3,000 Hours of Egocentric Video2110.07058v3 · Kristen Grauman, Andrew Westbury, Eugene Byrne et al.2021 · 628 citationsarXiv
D3D-HOI: Dynamic 3D Human-Object Interactions from Videos2108.08420v1 · Xiang Xu, Hanbyul Joo, Greg Mori et al.2021 · 17 citationsarXiv
FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration2108.06428v1 · Yu Rong, Takaaki Shiratori, Hanbyul Joo2021 · 216 citationsarXiv
3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data2011.00980v1 · Benjamin Biggs, S'ebastien Ehrhadt, Hanbyul Joo et al.2020 · 30 citationsarXiv
FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration2008.08324v1 · Yu Rong, Takaaki Shiratori, Hanbyul Joo2020 · 48 citationsarXiv
Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild2007.15649v2 · Jason Y. Zhang, Sam Pepose, Hanbyul Joo et al.2020 · 114 citationsarXiv
Body2Hands: Learning to Infer 3D Hands from Conversational Gesture Body Dynamics2007.12287v3 · Evonne Ng, Shiry Ginosar, Trevor Darrell et al.2020 · 52 citationsarXiv
Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation2004.03686v3 · Hanbyul Joo, Natalia Neverova, Andrea Vedaldi2020 · 187 citationsarXiv
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization2004.00452v1 · Shunsuke Saito, Tomas Simon, Jason Saragih et al.2020 · 794 citationsThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Single-Network Whole-Body Pose Estimation1909.13423v1 · Gines Hidalgo, Yaadhav Raaj, Haroon Idrees et al.2019 · 109 citationsarXiv
Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in A Triadic Interaction1906.04158v1 · Hanbyul Joo, Tomas Simon, Mina Cikara et al.2019 · 93 citationsarXiv
You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions1904.09882v2 · Evonne Ng, Donglai Xiang, Hanbyul Joo et al.2019 · 82 citationsarXiv
Capture Dense: Markerless Motion Capture Meets Dense Pose Estimation1812.01783v2 · Xiu Li, Yebin Liu, Hanbyul Joo et al.2018 · 1 citationarXiv
Monocular Total Capture: Posing Face, Body, and Hands in the Wild1812.01598v1 · Donglai Xiang, Hanbyul Joo, Yaser Sheikh2018 · 338 citationsarXiv
Structure from Recurrent Motion: From Rigidity to Recurrency1804.06510v1 · Xiu Li, Hongdong Li, Hanbyul Joo et al.2018 · 32 citationsarXiv
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies1801.01615v1 · Hanbyul Joo, Tomas Simon, Yaser Sheikh2018 · 510 citationsarXiv
Panoptic Studio: A Massively Multiview System for Social Interaction Capture.29990012 · Joo, Hanbyul, Simon, Tomas, Li, Xulong et al.2020 · 354 citationsIEEE transactions on pattern analysis and machine intelligence. 2019;41(1):190-204
Hand Keypoint Detection in Single Images using Multiview Bootstrapping1704.07809v1 · Tomas Simon, Hanbyul Joo, Iain Matthews et al.2017 · 1,147 citationsarXiv
Career total: 68 works. 50 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.