# PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

This repository profile is provided by osrepos.com, an open source repository discovery platform.

Source: osrepos.com
Repository profile: https://osrepos.com/repo/wgsxm-partcrafter
Generated for open source discovery and AI-assisted research.

PartCrafter is an innovative structured 3D generative model that enables the creation of complex 3D meshes and scenes from a single RGB image. Accepted at NeurIPS 2025, this project leverages compositional latent diffusion transformers to jointly generate multiple parts and objects in one shot. It offers powerful capabilities for both 3D object and scene generation, making it a valuable tool for researchers and developers in the field.

GitHub: https://github.com/wgsxm/PartCrafter
OSRepos URL: https://osrepos.com/repo/wgsxm-partcrafter

## Summary

PartCrafter is an innovative structured 3D generative model that enables the creation of complex 3D meshes and scenes from a single RGB image. Accepted at NeurIPS 2025, this project leverages compositional latent diffusion transformers to jointly generate multiple parts and objects in one shot. It offers powerful capabilities for both 3D object and scene generation, making it a valuable tool for researchers and developers in the field.

## Topics

- 3d generation
- 3d mesh
- latent diffusion
- transformers
- image to 3d
- python
- generative AI
- neurips

## Repository Information

Last analyzed by OSRepos: Wed Jan 14 2026 00:01:01 GMT+0000 (Western European Standard Time)
Detail views: 7
GitHub clicks: 4

## Safety Notice

OSRepos shares public repositories for knowledge and discovery only. Review source code, dependencies, licenses, and security implications before running or installing anything.

## Content

## Introduction

PartCrafter is a groundbreaking open-source project that introduces a structured 3D generative model capable of creating intricate 3D meshes and entire scenes from a single 2D RGB image. This research, accepted at NeurIPS 2025, utilizes Compositional Latent Diffusion Transformers to achieve its impressive results. Unlike traditional methods, PartCrafter can jointly generate multiple parts and objects in a single pass, offering a more holistic and efficient approach to 3D content creation. It provides robust solutions for both part-level 3D object generation and comprehensive 3D scene generation.

## Installation

To get PartCrafter up and running, follow these steps. The project recommends `torch-2.5.1+cu124` and `python-3.11`, though other versions might also work. A CUDA-enabled GPU with at least 8GB VRAM is required.

First, create a conda environment (optional):

bash
conda create -n partcrafter python=3.11.13
conda activate partcrafter
pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu124


Next, clone the repository and install dependencies:

bash
git clone https://github.com/wgsxm/PartCrafter.git
cd PartCrafter
bash settings/setup.sh


If you do not have root access and are using a conda environment, you can install required graphics libraries with:

bash
conda install -c conda-forge libegl libglu pyopengl


For Windows users, specific installation guides are available in [this pull request](https://github.com/wgsxm/PartCrafter/pull/24) and [this fork](https://github.com/JackDainzh/PartCrafter-Windows/tree/windows-main).

## Examples

PartCrafter offers quick start scripts for both 3D object and scene generation. The necessary model weights are automatically downloaded upon first use.

### 3D Part-Level Object Generation

Generate a 3D part-level object from an image:

bash
python scripts/inference_partcrafter.py \
  --image_path assets/images/np3_2f6ab901c5a84ed6bbdf85a67b22a2ee.png \
  --num_parts 3 --tag robot --render


Specify `--rmbg` if you use custom images. This will remove the background of the input image and resize it appropriately.

### 3D Scene Generation

Generate a 3D scene from an image:

bash
python scripts/inference_partcrafter_scene.py \
  --image_path assets/images_scene/np6_0192a842-531c-419a-923e-28db4add8656_DiningRoom-31158.png \
  --num_parts 6 --tag dining_room --render


## Why Use PartCrafter?

PartCrafter stands out for several compelling reasons:

*   **Cutting-edge Research**: Recognized and accepted at NeurIPS 2025, showcasing its significant contributions to the field of generative AI.
*   **Structured 3D Generation**: It uniquely generates 3D objects and scenes with distinct, compositionally structured parts, offering more control and realism.
*   **Image-to-3D Capability**: Seamlessly transforms 2D RGB images into complex 3D models and environments, streamlining the content creation pipeline.
*   **Advanced AI Architecture**: Leverages Compositional Latent Diffusion Transformers, a sophisticated approach for high-quality and coherent 3D outputs.
*   **Versatility**: Supports both detailed part-level object generation and expansive 3D scene construction, catering to diverse application needs.
*   **Open-Source and Accessible**: Fully open-sourced with pre-trained models available on HuggingFace, including an interactive demo for easy experimentation.

## Links

*   **GitHub Repository**: [https://github.com/wgsxm/PartCrafter](https://github.com/wgsxm/PartCrafter){:target="_blank"}
*   **Project Page**: [https://wgsxm.github.io/projects/partcrafter](https://wgsxm.github.io/projects/partcrafter){:target="_blank"}
*   **arXiv Paper**: [https://arxiv.org/abs/2506.05573](https://arxiv.org/abs/2506.05573){:target="_blank"}
*   **HuggingFace Demo**: [https://huggingface.co/spaces/alexnasa/PartCrafter](https://huggingface.co/spaces/alexnasa/PartCrafter){:target="_blank"}
*   **HuggingFace Model (Object)**: [https://huggingface.co/wgsxm/PartCrafter](https://huggingface.co/wgsxm/PartCrafter){:target="_blank"}
*   **HuggingFace Model (Scene)**: [https://huggingface.co/wgsxm/PartCrafter-Scene](https://huggingface.co/wgsxm/PartCrafter-Scene){:target="_blank"}
*   **YouTube Video**: [https://www.youtube.com/watch?v=ZaZHbkkPtXY](https://www.youtube.com/watch?v=ZaZHbkkPtXY){:target="_blank"}