Picture for Juze Zhang

Juze Zhang

HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment

Add code
Apr 02, 2024
Figure 1 for HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment
Figure 2 for HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment
Figure 3 for HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment
Figure 4 for HOI-M3:Capture Multiple Humans and Objects Interaction within Contextual Environment
Viaarxiv icon

BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics

Add code
Dec 20, 2023
Viaarxiv icon

I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions

Add code
Dec 10, 2023
Figure 1 for I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions
Figure 2 for I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions
Figure 3 for I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions
Figure 4 for I'M HOI: Inertia-aware Monocular Capture of 3D Human-Object Interactions
Viaarxiv icon

IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation

Add code
Feb 12, 2023
Figure 1 for IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation
Figure 2 for IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation
Figure 3 for IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation
Figure 4 for IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation
Viaarxiv icon

NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions

Dec 15, 2022
Figure 1 for NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions
Figure 2 for NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions
Figure 3 for NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions
Figure 4 for NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactions
Viaarxiv icon

Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR

Add code
Nov 30, 2022
Figure 1 for Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR
Figure 2 for Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR
Figure 3 for Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR
Figure 4 for Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR
Viaarxiv icon

Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation

Jul 16, 2022
Figure 1 for Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation
Figure 2 for Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation
Figure 3 for Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation
Figure 4 for Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation
Viaarxiv icon

Compressed Sensing for Photoacoustic Computed Tomography Using an Untrained Neural Network

May 29, 2021
Figure 1 for Compressed Sensing for Photoacoustic Computed Tomography Using an Untrained Neural Network
Figure 2 for Compressed Sensing for Photoacoustic Computed Tomography Using an Untrained Neural Network
Figure 3 for Compressed Sensing for Photoacoustic Computed Tomography Using an Untrained Neural Network
Figure 4 for Compressed Sensing for Photoacoustic Computed Tomography Using an Untrained Neural Network
Viaarxiv icon