diff --git a/README.md b/README.md index 4cdf98d..08564ed 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -# EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence +# *EmbodiedGen*: Towards a Generative 3D World Engine for Embodied Intelligence [![🌐 Project Page](https://img.shields.io/badge/🌐-Project_Page-blue)](https://horizonrobotics.github.io/robot_lab/embodied_gen/index.html) [![📄 arXiv](https://img.shields.io/badge/📄-arXiv-b31b1b)](https://arxiv.org/abs/2506.10600) @@ -8,8 +8,8 @@ [![🤗 Hugging Face](https://img.shields.io/badge/🤗-Texture_Gen_Demo-blue)](https://huggingface.co/spaces/HorizonRobotics/EmbodiedGen-Texture-Gen) -**EmbodiedGen** is a toolkit to generate diverse and interactive 3D worlds composed of generative 3D assets with plausible physics, leveraging generative AI to address the challenges of generalization in embodied intelligence related research. EmbodiedGen composed of six key modules: `Image-to-3D`, `Text-to-3D`, `Texture Generation`, `Articulated Object Generation`, `Scene Generation` and `Layout Generation`. - +> ***EmbodiedGen*** is a generative engine to create diverse and interactive 3D worlds composed of high-quality 3D assets(mesh & 3DGS) with plausible physics, leveraging generative AI to address the challenges of generalization in embodied intelligence related research. +> It composed of six key modules: `Image-to-3D`, `Text-to-3D`, `Texture Generation`, `Articulated Object Generation`, `Scene Generation` and `Layout Generation`. Overall Framework @@ -21,7 +21,7 @@ - [🎨 Texture Generation](#texture-generation) - [🌍 3D Scene Generation](#3d-scene-generation) - [⚙️ Articulated Object Generation](#articulated-object-generation) -- [🏞️ Layout Generation](#layout-generation) +- [🏞️ Layout(Interactive 3D Worlds) Generation](#layout-generation) ## 🚀 Quick Start @@ -36,7 +36,7 @@ conda activate embodiedgen bash install.sh ``` -### 🟢 Setup GPT Agent +### ✅ Setup GPT Agent Update the API key in file: `embodied_gen/utils/gpt_config.yaml`. @@ -50,13 +50,13 @@ You can choose between two backends for the GPT agent:

🖼️ Image-to-3D

-[![🤗 Hugging Face](https://img.shields.io/badge/🤗-Image_to_3D_Demo-blue)](https://huggingface.co/spaces/HorizonRobotics/EmbodiedGen-Image-to-3D) Generate physically plausible 3D asset from input image. +[![🤗 Hugging Face](https://img.shields.io/badge/🤗-Image_to_3D_Demo-blue)](https://huggingface.co/spaces/HorizonRobotics/EmbodiedGen-Image-to-3D) Generate physically plausible 3D asset URDF from single input image, offering high-quality support for digital twin systems. Image to 3D -### Service -Run the image-to-3D generation service locally. The first run will download required models. - +### ☁️ Service +Run the image-to-3D generation service locally. +Models downloaded automatically on first run, please be patient. ```sh # Run in foreground python apps/image_to_3d.py @@ -64,13 +64,12 @@ python apps/image_to_3d.py CUDA_VISIBLE_DEVICES=0 nohup python apps/image_to_3d.py > /dev/null 2>&1 & ``` -### API -Generate a 3D model from an image using the command-line API. -Models will be downloaded automatically, please wait for the first run. +### ⚡ API +Generate physically plausible 3D assets from image input via the command-line API. ```sh python3 embodied_gen/scripts/imageto3d.py \ --image_path apps/assets/example_image/sample_04.jpg apps/assets/example_image/sample_19.jpg \ - --output_root outputs/imageto3d/ + --output_root outputs/imageto3d # See result(.urdf/mesh.obj/mesh.glb/gs.ply) in ${output_root}/sample_xx/result ``` @@ -84,19 +83,21 @@ python3 embodied_gen/scripts/imageto3d.py \ Text to 3D -### Service -Run the text-to-3D generation service locally. +### ☁️ Service +Deploy the text-to-3D generation service locally. +Text-to-image based on the Kolors model, supporting Chinese and English prompts. +Models downloaded automatically on first run, see `download_kolors_weights`, please be patient. ```sh python apps/text_to_3d.py ``` -### API -Models will be downloaded automatically, see `download_kolors_weights`. +### ⚡ API +Text-to-image based on the Kolors model. ```sh bash embodied_gen/scripts/textto3d.sh \ --prompts "small bronze figurine of a lion" "A globe with wooden base and latitude and longitude lines" "橙色电动手钻，有磨损细节" \ - --output_root outputs/textto3d/ + --output_root outputs/textto3d ``` --- @@ -109,15 +110,14 @@ bash embodied_gen/scripts/textto3d.sh \ Texture Gen -### Service +### ☁️ Service Run the texture generation service locally. - +Models downloaded automatically on first run, see `download_kolors_weights`, `geo_cond_mv`. ```sh python apps/texture_edit.py ``` -### API -Models will be downloaded automatically, see `download_kolors_weights`, `geo_cond_mv`. +### ⚡ API ```sh bash embodied_gen/scripts/texture_gen.sh \ --mesh_path "apps/assets/example_texture/meshes/robot_text.obj" \ @@ -147,7 +147,25 @@ bash embodied_gen/scripts/texture_gen.sh \ --- -

🏞️ Layout Generation

+

🏞️ Layout(Interactive 3D Worlds) Generation

+ +### 💬 Generate Layout from task description + +🚧 *Coming Soon* + + + + + + + + + + +
layout1layout2
layout3layout4
+ + +### 🖼️ Generate Layout from image 🚧 *Coming Soon* @@ -176,9 +194,8 @@ If you use EmbodiedGen in your research or projects, please cite: EmbodiedGen builds upon the following amazing projects and models: 🌟 [Trellis](https://github.com/microsoft/TRELLIS) | 🌟 [Hunyuan-Delight](https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-delight-v2-0) | 🌟 [Segment Anything](https://github.com/facebookresearch/segment-anything) | 🌟 [Rembg](https://github.com/danielgatis/rembg) | 🌟 [RMBG-1.4](https://huggingface.co/briaai/RMBG-1.4) | 🌟 [Stable Diffusion x4](https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler) | 🌟 [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) | 🌟 [Kolors](https://github.com/Kwai-Kolors/Kolors) | 🌟 [ChatGLM3](https://github.com/THUDM/ChatGLM3) | 🌟 [Aesthetic Score](http://captions.christoph-schuhmann.de/aesthetic_viz_laion_sac+logos+ava1-l14-linearMSE-en-2.37B.html) | 🌟 [Pano2Room](https://github.com/TrickyGo/Pano2Room) | 🌟 [Diffusion360](https://github.com/ArcherFMY/SD-T2I-360PanoImage) | 🌟 [Kaolin](https://github.com/NVIDIAGameWorks/kaolin) | 🌟 [diffusers](https://github.com/huggingface/diffusers) | 🌟 [gsplat](https://github.com/nerfstudio-project/gsplat) | 🌟 [QWEN2.5VL](https://github.com/QwenLM/Qwen2.5-VL) | 🌟 [GPT4o](https://platform.openai.com/docs/models/gpt-4o) - --- ## ⚖️ License -This project is licensed under the [Apache License 2.0](LICENSE). See the `LICENSE` file for details. \ No newline at end of file +This project is licensed under the [Apache License 2.0](LICENSE). See the `LICENSE` file for details. diff --git a/apps/assets/layout1.gif b/apps/assets/layout1.gif new file mode 100644 index 0000000..eee2902 Binary files /dev/null and b/apps/assets/layout1.gif differ diff --git a/apps/assets/layout2.gif b/apps/assets/layout2.gif new file mode 100644 index 0000000..7c7524e Binary files /dev/null and b/apps/assets/layout2.gif differ diff --git a/apps/assets/layout3.gif b/apps/assets/layout3.gif new file mode 100644 index 0000000..be948d6 Binary files /dev/null and b/apps/assets/layout3.gif differ diff --git a/apps/assets/layout4.gif b/apps/assets/layout4.gif new file mode 100644 index 0000000..6816f93 Binary files /dev/null and b/apps/assets/layout4.gif differ