All effects

C = Σ cᵢ αᵢ Π (1 − αⱼ)

Gaussian splatting.

1990 to now

No triangles, no distance field, just tens of thousands of soft, coloured, stretched blobs, sorted and blended. Since 2023 it can render captured reality in real time, and the demoscene is only starting to find out what it can do as an effect.

ResearchEmerging

How it works

The algorithm

A scene is a cloud of 3D Gaussians, each with a position, a covariance (its size and orientation, like a squashed ellipsoid), a colour and an opacity. Every frame, project each Gaussian to the screen, the Jacobian of the perspective projection turns its 3D covariance into a 2D ellipse, sort them by depth and alpha-blend them back to front. In the 2023 method the Gaussians are optimised against photographs, so the cloud reproduces a real place.

Why it needs today's hardware

It only became practical because of current hardware: millions of splats need a GPU that can sort and blend them every frame. The tricks are a fast radix or counting sort on depth, drawing each splat as one instanced quad sized to 3σ of its ellipse, and premultiplied alpha blending. Nothing is spent on empty space, unlike volume ray marching.

Per frame, in pseudo-code
for g in gaussians:                       // 3D → 2D
  c = view · g.position
  J = ∂(screen)/∂(camera) at c            // perspective Jacobian
  Σ₂ = J · R · g.Σ · Rᵀ · Jᵀ + 0.3·I
  ellipse = eigen(Σ₂)  → quad of ±3σ

sort gaussians by c.z, far to near
for g in sorted:                          // per pixel of its quad
  α = g.opacity · exp(−½ dᵀ Σ₂⁻¹ d)
  pixel = pixel·(1 − α) + g.colour·α

Timeline

Documented milestones, with a source for each. Famous examples, not claims of who did it first.

  1. 1990Research

    Splatting

    Lee Westover · SIGGRAPH 1990 · Volume rendering research

    ‘Footprint evaluation for volume rendering’: instead of casting rays, each data sample is projected and its footprint spread onto the image, the word and the idea of splatting.

    Source
  2. 2000Research

    QSplat

    Szymon Rusinkiewicz & Marc Levoy · Point-based rendering

    Huge scanned models rendered interactively as hierarchies of point splats, points instead of triangles.

    Source
  3. 2001Research

    Surface splatting (EWA)

    Zwicker, Pfister, van Baar & Gross · SIGGRAPH 2001 · Point-based rendering

    Each point becomes an elliptical Gaussian filtered in screen space, the projection maths that 3D Gaussian splatting still uses.

    Source
  4. 2023Emerging

    3D Gaussian Splatting

    Kerbl, Kopanas, Leimkühler & Drettakis · SIGGRAPH 2023 · Native GPU · CUDA

    Anisotropic Gaussians optimised against photos render captured scenes at 100+ fps at 1080p. The original implementation uses CUDA, not the fixed rasterisation pipeline.

    Source
  5. 2023Emerging

    Splats in the browser

    cvlab-epfl (WebGPU) · antimatter15 (WebGL) · Browser · WebGPU / WebGL

    Within weeks, open viewers render trained scenes in a browser tab, first in WebGPU (August), then in plain WebGL (September).

    Source
  6. 2023Emerging

    In a game engine

    Aras Pranckevičius · UnityGaussianSplatting · Unity · GPU

    Playback of trained splat models inside a general-purpose engine, training and real-time display become separate steps.

    Source
  7. 2024Emerging

    Interactive splat scenes

    Equinor summer interns · Browser · Three.js

    Gaussian objects mixed with ordinary 3D objects, including a bowling demo with splat pins, interaction beyond passive viewing.

    Source
  8. 2026Emerging

    Gaussians in a 4K

    With Love · I see you · 4K procedural graphics

    A 4K executable still whose author confirms about 450 fitted Gaussian splats, fitting an image, not a 3D fly-through. The scene is only starting to use them.

    Source

Over time

5 live versions, from the oldest platform to today: 3 on the CPU, 2 on the GPU. Retro versions run at their original resolution and palette. Demos pause when off screen.

CPU · QSplat-style

Point splats

2000

The scene's 23,000 points drawn as opaque squares sized by distance, back to front. You can see the object, and every point.

ResearchCPUpointspainter's algorithm
Detail page
CPU · software

EWA on the CPU

2001

Same points, now as proper elliptical Gaussians: each 3D covariance projected with the perspective Jacobian and alpha-blended per pixel, in JavaScript, at 200 pixels wide.

ResearchCPUcovariancealpha blending
Detail page
GPU · WebGL2

3D Gaussian splatting

2023

Our own procedural ‘capture’: a knot, a disc, floating spheres, sky and dust, 23,000 anisotropic Gaussians, depth-sorted every frame with a counting sort and drawn as instanced quads.

EmergingGPU3DGSinstancing
Detail page
GPU · WebGL2

Splat morph

now

Splats as a demo effect: 8,300 Gaussians flow from a sphere into a knot and back, each with its own delay, re-sorted every frame as they pass through each other.

EmergingGPUmorphemerging
Detail page
CPU · 2D Gaussians

Fitted image

2026

An image built from 1,400 stretched 2D Gaussians, added coarse to fine like an optimiser at work: big soft ones for the background, thin ones along the edges.

EmergingCPU2Dcoarse to fine
Detail page