[AAAI 2026] FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework

Official Code——HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception

Official implementation of CVPR24 highlight paper "Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance"

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

CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control

Official implementation of TeSMo, a method for text-controlled scene-aware motion generation, from the ECCV 2024 paper: "Generating Human Interaction Motions in Scenes with Text Control".

[ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts

Repository of TRUMANS

[ICCV 2023] Official PyTorch implementation of the paper "InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion"

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

We introduce DiffH2O, a diffusion-based framework to synthesize dexterous hand-object interactions. DiffH2O generates realistic hand-object motion from natural language, generalizes to unseen objec…

[CVPR 2025] InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation

A system for generating diverse, physically compliant 3D human motions across multiple motion types, guided by plot contexts to streamline creative workflows in anime and game design.

[ICCV'25] Method for generating static human-object interactions

This repository collects papers on Human-Interaction-Motion-Generation applications. We will update new papers irregularly.

A list of Human-Object Interaction Learning.

Official Implementation of the Paper: Controllable Human-Object Interaction Synthesis (ECCV 2024 Oral)

HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models, arXiv 2023

PyTorch implementation of Pointnet2/Pointnet++

[Technical Report 2023] PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction

Lightweight head for semantic segmentation using DINOv3 as backbone

first commit

All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.

Switch the backbone of mask2former to DINOv3 for instance segmentation

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios

This is an implementation of zero-shot instance segmentation using Segment Anything.

PA-SAM: Prompt Adapter SAM for High-quality Image Segmentation