GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
This addresses the need for fast and high-quality 3D reconstruction in fields like computer vision and graphics, though it appears incremental as it builds on existing transformer and Gaussian methods.
The paper tackles the problem of 3D reconstruction from sparse-view images by introducing GRM, a transformer-based model that recovers 3D assets in about 0.1 seconds with superior quality and efficiency compared to alternatives.
We introduce GRM, a large-scale reconstructor capable of recovering a 3D asset from sparse-view images in around 0.1s. GRM is a feed-forward transformer-based model that efficiently incorporates multi-view information to translate the input pixels into pixel-aligned Gaussians, which are unprojected to create a set of densely distributed 3D Gaussians representing a scene. Together, our transformer architecture and the use of 3D Gaussians unlock a scalable and efficient reconstruction framework. Extensive experimental results demonstrate the superiority of our method over alternatives regarding both reconstruction quality and efficiency. We also showcase the potential of GRM in generative tasks, i.e., text-to-3D and image-to-3D, by integrating it with existing multi-view diffusion models. Our project website is at: https://justimyhxu.github.io/projects/grm/.