Wiredwisdom

Our goals are to have fast overall rendering and fast sorting to allow approximate 𝛼-blending – including for anisotropic splats – and to avoid hard limits on the number of splats that can receive gradients that exist in previous work [Lassner and Zollhofer 2021]. To achieve these goals, we design a tile-based rasterizer for Gaussian splats inspired by recent software rasterization approaches [..

This diagram illustrates the complete pipeline of 3D Gaussian Splatting rendering system. The workflow begins with 3D Gaussians that undergo projection mapping to convert 3D spatial information into 2D screen coordinates. The projected data then passes through a Differentiable Tile Rasterizer, which determines how to traverse and process Gaussians per pixel, ultimately generating the rendered im..