Download
SAM 3D Objects is a foundation model that reconstructs full 3D geometry, texture, and spatial layout of objects and scenes from a single image. Given one RGB image and object masks (for example, from the Segment Anything family), it can generate a textured 3D mesh for each object, including pose and approximate scene layout. The model is specifically designed to be robust in real-world images with clutter, occlusions, small objects, and unusual viewpoints, where many earlier 3D-from-image systems struggle. It supports both single-object and multi-object generation, allowing you to reconstruct entire scenes rather than just isolated items. The repository provides code to run inference, a quickstart demo.py script, and environment setup instructions that connect to hosted checkpoints and configuration files. Outputs are aimed at downstream usability: the reconstructed assets are textured meshes suitable for further editing, rendering, or integration into 3D pipelines and engines.
Features
- Single-image 3D reconstruction of objects and full scenes, including pose, geometry, texture, and layout
- Works with masked regions to turn 2D object segments into textured 3D meshes
- Designed for robustness in natural, uncurated images with clutter, occlusions, and small objects
- Supports both single-object and multi-object generation modes from the same image
- Python demo script and API for quick inference and integration into 3D workflows
- Checkpoints and configs released for research use, forming the object half of the SAM 3D model family
Project Samples
