# 3D Gaussian splatting

3D Gaussian splatting is a 2023 technique that represents scenes as millions of oriented 3D Gaussians, achieving photorealistic novel-view synthesis with real-time rendering and largely displacing NeRF in practical use.

3D Gaussian splatting is a scene representation and rendering technique that models a three-dimensional scene as a large set of oriented, semi-transparent 3D Gaussians, each with position, shape, color and opacity. Introduced in the 2023 SIGGRAPH paper "3D Gaussian Splatting for Real-Time Radiance Field Rendering" by Bernhard Kerbl, Georgios Kopanas, Thomas Leimkuehler and George Drettakis of Inria and the Max Planck Institute, it matched or exceeded the visual quality of [neural radiance fields](https://www.wikiprompt.org/wiki/nerf) while rendering at real-time frame rates, and quickly became the dominant approach to novel-view synthesis.

## How it works

Starting from a sparse point cloud produced by classical structure-from-motion, each point becomes a 3D Gaussian whose parameters are optimized by [gradient descent](https://www.wikiprompt.org/wiki/gradient-descent) so that rasterized renderings match the input photographs. Unlike a NeRF, which stores the scene implicitly in [neural network](https://www.wikiprompt.org/wiki/neural-network) weights and renders by costly ray sampling, Gaussian splatting is an explicit representation rendered by fast [GPU](https://www.wikiprompt.org/wiki/gpu) rasterization: Gaussians are projected, or "splatted", onto the image plane and alpha-blended in depth order. Densification and pruning during training add detail where needed and remove redundant primitives.

## Adoption

Within a year of publication the method spread through visual effects, game engines, drone mapping, real-estate capture and smartphone scanning apps, with support landing in Unreal Engine, Unity and consumer capture tools. Research extensions added dynamic scenes, animatable human avatars, and integration with [text-to-3D generation](https://www.wikiprompt.org/wiki/text-to-3d) pipelines, where splats serve as the optimized representation. The technique also feeds [embodied AI](https://www.wikiprompt.org/wiki/embodied-ai) and robotics simulation, producing photoreal environments from casual video capture.

## Relation to the field

Gaussian splatting is often described as the practical successor to NeRF: both belong to the radiance-field family born from [computer vision](https://www.wikiprompt.org/wiki/computer-vision) and [deep learning](https://www.wikiprompt.org/wiki/deep-learning) research, but splatting trades implicit neural compactness for explicit primitives and rendering speed. Active research explores compression, relighting and hybrid neural-explicit models.

---
Source: https://www.wikiprompt.org/wiki/gaussian-splatting
License: CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/)
Last updated: 2026-09-02T22:00:31.443501+00:00