TripoSR, developed by Tripo and Stability AI, is a cutting-edge open-source model designed for fast 3D reconstruction from a single image. It generates high-quality 3D models in under a second, making it suitable for various applications in entertainment, gaming, industrial design, and architecture.
TripoSR can create detailed 3D models much faster than other methods. When tested on an Nvidia A100, it generates draft-quality 3D outputs (textured meshes) in about 0.5 seconds, outperforming other open image-to-3D models like OpenLRM. Besides its speed, this model is fully accessible to users with or without GPUs.
The training data preparation incorporates diverse data rendering techniques that accurately replicate the distribution of images found in the real world, significantly enhancing the model's ability to generalize. It meticulously curates a CC-BY, a superior-quality subset of the Objaverse dataset, for the training data. On the model side, it introduces several technical advancements over the base LRM model, including channel number optimization, mask supervision, and a more efficient crop rendering strategy. You can read the technical report for more details.
TripoSR invites developers, designers, and creators to explore its capabilities, contribute to its evolution, and discover its potential to transform their work and industries.
The code for the TripoSR model is now available on Tripo AI’s GitHub, and the model weights are available on Hugging Face. Please refer to our technical report for more details on the TripoSR model.