articleJun 16, 2024Closed access

PixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

Massachusetts Institute of Technology · University of Toronto · +1 more institution

Indexed incrossref

Abstract

We introduce pixelSplat, a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images. Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time. To overcome local minima inherent to sparse and locally supported representations, we predict a dense probability distribution over 3D and sample Gaussian means from that probability distribution. We make this sampling operation differentiable via a reparameterization trick, allowing us to back-propagate gradients through the Gaussian splatting representation. We benchmark our method on wide-baseline novel view synthesis on…

Citation impact

187
total citations
FWCI
103.27
Percentile
100%
References
70
Citations per year

Authors

4

Topics & keywords

Keywords
  • Computer science
  • Scalability
  • Gaussian
  • Iterative reconstruction
  • Artificial intelligence
  • Computer vision
  • Image (mathematics)
  • Gaussian process
No related works found for this paper.

Funding