GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
arxiv(2024)
摘要
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/.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要