GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting

Kai Zhang^*1, Sai Bi^*1, Hao Tan^*1, Yuanbo Xiangli², Nanxuan Zhao¹, Kalyan Sunkavalli¹, Zexiang Xu¹ ^*(Equal contribution)
¹Adobe Research ²Cornell University

arXiv Cite

High-quality 3D Gaussian primitives from 2-4 posed sparse images within 0.23 second

(This webpage contains a lot of videos and interactive viewers. We suggest using Chrome or Edge for the best experience)

Results on Amazon Berkeley Objects

(Click to return to homepage)

Open interactive viewer

BibTeX

@article{gslrm2024,
    author={Zhang, Kai and Bi, Sai and Tan, Hao and Xiangli, Yuanbo and Zhao, Nanxuan 
      and Sunkavalli, Kalyan and Xu, Zexiang},
    title     = {GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting},
    journal   = {arXiv},
    year      = {2024},
}