Skip to content

image_to_3d.md

Latest commit

 

History

History
72 lines (61 loc) · 2.77 KB

image_to_3d.md

File metadata and controls

72 lines (61 loc) · 2.77 KB

🖼️ Image-to-3D: Physically Plausible 3D Asset Generation

Generate physically plausible 3D assets from a single input image, supporting digital twin and simulation environments.

⚡ Command-Line Usage

Support the use of SAM3D or TRELLIS as 3D generation model, modify IMAGE3D_MODEL in embodied_gen/scripts/imageto3d.py to switch model.

img3d-cli --image_path apps/assets/example_image/sample_00.jpg \
apps/assets/example_image/sample_01.jpg \
--n_retry 2 --output_root outputs/imageto3d

You will get the following results:

The generated results are organized as follows:

outputs/imageto3d/sample_xx/result
├── mesh
│   ├── material_0.png
│   ├── material.mtl
│   ├── sample_xx_collision.ply
│   ├── sample_xx.glb
│   ├── sample_xx_gs.ply
│   └── sample_xx.obj
├── sample_xx.urdf
└── video.mp4
  • mesh/ → Geometry and texture files, including visual mesh, collision mesh and 3DGS.
  • *.urdf → Simulator-ready URDF with collision and visual meshes
  • video.mp4 → Preview of the generated 3D asset

!!! tip "Getting Started" - Try it directly online via our Hugging Face Space — no installation required. - Explore EmbodiedGen generated sim-ready Assets Gallery. - For instructions on using the generated asset in any simulator, see Any Simulators Tutorial.