Litcius/Paper detail

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

David Charatan, Sizhe Li, Andrea Tagliasacchi, Vincent Sitzmann

2024191 citationsDOI

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 the real-world RealEstate10k and ACID datasets, where we outperform state-of-the-art light field transformers and accelerate rendering by 2.5 orders of magnitude while reconstructing an interpretable and ed-itable 3D radiance field. Additional materials can be found on the project website.<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>dcharatan.github.io/pixelsplat

Topics & Concepts

Computer scienceScalabilityGaussianIterative reconstructionArtificial intelligenceComputer visionImage (mathematics)Gaussian processComputer graphics (images)Pattern recognition (psychology)PhysicsDatabaseQuantum mechanicsComputer Graphics and Visualization Techniques3D Shape Modeling and AnalysisAdvanced Vision and Imaging