Hongwei Yi

papers

1,384

total citations

papers (14)

SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments

CVPR 2023arXiv

citations

High-Fidelity Clothed Avatar Reconstruction From a Single Image

CVPR 2023arXiv

citations

One-shot Implicit Animatable Avatars with Model-based Priors

ICCV 2023arXiv

citations

DECO: Dense Estimation of 3D Human-Scene Contact In The Wild

ICCV 2023arXiv

citations

MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization

ICCV 2025arXiv

citations

ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

CVPR 2024arXiv

citations

Test-time Personalizable Forecasting of 3D Human Poses

ICCV 2023

citations

Hongwei Yi

papers (14)

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking

Generating Holistic 3D Human Motion From Speech

Capturing and Inferring Dense Full-Body Human-Scene Contact

Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation

Human-Aware Object Placement for Visual Environment Reconstruction

MIME: Human-Aware 3D Scene Generation

SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments

High-Fidelity Clothed Avatar Reconstruction From a Single Image

One-shot Implicit Animatable Avatars with Model-based Priors

DECO: Dense Estimation of 3D Human-Scene Contact In The Wild

MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization

ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

Test-time Personalizable Forecasting of 3D Human Poses

papers (14)

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking

Generating Holistic 3D Human Motion From Speech

Capturing and Inferring Dense Full-Body Human-Scene Contact

Pyramid Multi-view Stereo Net with Self-adaptive View Aggregation

Human-Aware Object Placement for Visual Environment Reconstruction

MIME: Human-Aware 3D Scene Generation

SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments

High-Fidelity Clothed Avatar Reconstruction From a Single Image

One-shot Implicit Animatable Avatars with Model-based Priors

DECO: Dense Estimation of 3D Human-Scene Contact In The Wild

MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization

ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

Test-time Personalizable Forecasting of 3D Human Poses