2D Gaussian Splatting for Geometrically Accurate Radiance Fields We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images Our key idea is to collapse the 3D volume into a set of 2D oriented planar Gaussian disks
2D Gaussian Splatting for Geometrically Accurate Radiance Fields This repo contains the official implementation for the paper "2D Gaussian Splatting for Geometrically Accurate Radiance Fields" Our work represents a scene with a set of 2D oriented disks (surface elements) and rasterizes the surfels with perspective correct differentiable raseterization
GitHub Pages - 2D Gaussian Splatting We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images Our key idea is to collapse the 3D volume into a set of 2D oriented planar Gaussian disks
2D Gaussian Splatting: Radiance Field Reconstruction Discover how 2D Gaussian Splatting transforms neural rendering by replacing volumetric 3D Gaussians with surface-aligned 2D disks 2D Gaussian Splatting, being a breakthrough in neural rendering, brings a new level of geometric precision to radiance field reconstruction
“2D Gaussian Splatting for Geometrically Accurate Radiance Fields . . . It employs perspective-accurate 2D splatting, integrates depth distortion and normal consistency for improved reconstructions, and offers detailed geometry reconstruction with fast training and real-time rendering through a differentiable renderer