Structured 3D Latents for Scalable and Versatile 3D Generation
JeffreyXiang
Abstract
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.
Community
TRELLIS is a large 3D asset generation model. It takes in text or image prompts and generates high-quality 3D assets in various formats, such as Radiance Fields, 3D Gaussians, and meshes. The cornerstone of TRELLIS is a unified Structured LATent (SLAT) representation that allows decoding to different output formats and Rectified Flow Transformers tailored for SLAT as the powerful backbones. We provide large-scale pre-trained models with up to 2 billion parameters on a large 3D asset dataset of 500K diverse objects. TRELLIS significantly surpasses existing methods, including recent ones at similar scales, and showcases flexible output format selection and local 3D editing capabilities which were not offered by previous models.
Project Page: https://trellis3d.github.io
Code: https://github.com/Microsoft/TRELLIS
Demo: https://huggingface.co/spaces/JeffreyXiang/TRELLIS
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation (2024)
- Direct and Explicit 3D Generation from a Single Image (2024)
- Edify 3D: Scalable High-Quality 3D Asset Generation (2024)
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (2024)
- RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image (2024)
- L3DG: Latent 3D Gaussian Diffusion (2024)
- GSEditPro: 3D Gaussian Splatting Editing with Attention-based Progressive Localization (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
This moves humanity to the expanses of the universe. Make a CAD AI editor so that you can design robots that will fly for resources to the nearest asteroid belt to produce an abundance of things that satisfy all the needs of all humanity. I think that people will strive to space for a safer and more comfortable life than now on earth. There is enough space and resources in the universe for everyone.
a 3D model of power socket
