Hyeongjin Nam

[ECCV 2022] This repo is official PyTorch implementation of 3D Clothed Human Reconstruction in the Wild.

[CVPR 2024] This repo is official PyTorch implementation of Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer.

[ICCV 2023] This repo is official PyTorch implementation of Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction.

[CVPR 2026] This repo is official implementation of TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures.

[ICCV 2025] This repo is an official PyTorch implementation of PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image.

This repository is the implementation of an automatic human hazard detection model based on a human posture. Collaborated with SNU HIS LAB.

This code is an exercise code based on Mask R-CNN released in 2018.

[CVPR 2026] CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction

Project submission code for the 'Embedded Systems and Applications' course.

No description.

[CVPR 2025 Highlight] InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions

MagicTryOn is a video virtual try-on framework based on a large-scale video diffusion Transformer.

This is the official repository of SIGGRAPH Asia 2024 Paper: Autonomous Character-Scene Interaction Synthesis from Text Instruction

Repository of TRUMANS

[CVPR 2025] InteractVLM: 3D Interaction Reasoning from 2D Foundational Models

No description.

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

[CVPR 2025] PICO: Reconstructing 3D People In Contact with Objects

A simple baseline with QwenVL-2.5

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

Implementation for the paper `Monocular Human-Object Reconstruction in the Wild`

Evaluation of Visual Grounding Methods For ICCV 2025 MARS2 Workshop