Hanbyul Joo

papers

3,345

total citations

papers (21)

Ego4D: Around the World in 3,000 Hours of Egocentric Video

CVPR 2022arXiv

1,511

citations

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

CVPR 2020arXiv

829

citations

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

CVPR 2020arXiv

106

citations

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

NEURIPS 2020arXiv

citations

Body2Hands: Learning To Infer 3D Hands From Conversational Gesture Body Dynamics

CVPR 2021arXiv

citations

Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments

ICCV 2023arXiv

citations

ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions

CVPR 2025arXiv

citations

Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera

CVPR 2024arXiv

citations

GALA: Generating Animatable Layered Assets from a Single Scan

CVPR 2024arXiv

citations

Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models

ICCV 2023arXiv

citations

CHORUS : Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images

ICCV 2023arXiv

citations

Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses

CVPR 2024arXiv

citations

NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects

ICCV 2023arXiv

citations

DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models

ICCV 2025arXiv

citations

PERSE: Personalized 3D Generative Avatars from A Single Portrait

CVPR 2025arXiv

citations

PEGASUS: Personalized Generative 3D Avatars with Composable Attributes

CVPR 2024arXiv

citations

Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models

ICCV 2025arXiv

citations

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars

ICCV 2025arXiv

citations

Hanbyul Joo

papers (21)

Ego4D: Around the World in 3,000 Hours of Egocentric Video

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

BANMo: Building Animatable 3D Neural Models From Many Casual Videos

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

Learning To Listen: Modeling Non-Deterministic Dyadic Facial Motion

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

Body2Hands: Learning To Infer 3D Hands From Conversational Gesture Body Dynamics

Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments

ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions

Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera

GALA: Generating Animatable Layered Assets from a Single Scan

Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models

CHORUS : Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images

Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses

NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects

DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models

PERSE: Personalized 3D Generative Avatars from A Single Portrait

PEGASUS: Personalized Generative 3D Avatars with Composable Attributes

Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars

papers (21)

Ego4D: Around the World in 3,000 Hours of Egocentric Video

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

BANMo: Building Animatable 3D Neural Models From Many Casual Videos

Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

Learning To Listen: Modeling Non-Deterministic Dyadic Facial Motion

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

Body2Hands: Learning To Infer 3D Hands From Conversational Gesture Body Dynamics

Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments

ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions

Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera

GALA: Generating Animatable Layered Assets from a Single Scan

Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models

CHORUS : Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images

Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses

NCHO: Unsupervised Learning for Neural 3D Composition of Humans and Objects

DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models

PERSE: Personalized 3D Generative Avatars from A Single Portrait

PEGASUS: Personalized Generative 3D Avatars with Composable Attributes

Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars