Structured 3D Latents for Scalable and Versatile 3D Generation
This addresses the need for scalable and flexible 3D generation tools for creators and developers, offering novel capabilities like format selection and editing, though it builds incrementally on prior latent and transformer-based approaches.
The paper tackles the problem of versatile and high-quality 3D asset generation by introducing a Structured LATent (SLAT) representation that decodes to formats like Radiance Fields and meshes, achieving significant improvements over existing methods with a model trained on 500K objects and up to 2 billion parameters.
We introduce a novel 3D generation method for versatile and high-quality 3D asset creation. The cornerstone is a unified Structured LATent (SLAT) representation which allows decoding to different output formats, such as Radiance Fields, 3D Gaussians, and meshes. This is achieved by integrating a sparsely-populated 3D grid with dense multiview visual features extracted from a powerful vision foundation model, comprehensively capturing both structural (geometry) and textural (appearance) information while maintaining flexibility during decoding. We employ rectified flow transformers tailored for SLAT as our 3D generation models and train models with up to 2 billion parameters on a large 3D asset dataset of 500K diverse objects. Our model generates high-quality results with text or image conditions, significantly surpassing existing methods, including recent ones at similar scales. We showcase flexible output format selection and local 3D editing capabilities which were not offered by previous models. Code, model, and data will be released.