# graphdeco-inria/gaussian-splatting

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/graphdeco-inria-gaussian-splatting).**

20,707 stars · 2,970 forks · Python · other

## Links

- GitHub: https://github.com/graphdeco-inria/gaussian-splatting
- Homepage: https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/
- awesome-repositories: https://awesome-repositories.com/repository/graphdeco-inria-gaussian-splatting.md

## Topics

`computer-graphics` `computer-vision` `radiance-field`

## Description

Gaussian Splatting is a computational framework designed to transform sparse sets of two-dimensional photographs into photorealistic, interactive three-dimensional scene representations. The system functions as a reconstruction tool and rendering engine, enabling the conversion of image data into volumetric models that support novel view synthesis.

The project represents scenes as a collection of anisotropic three-dimensional Gaussians, which store position, opacity, color, and covariance data. It distinguishes itself through a differentiable tile-based rasterization process that projects these primitives into image space, combined with adaptive density control that dynamically splits or prunes primitives to maintain high-fidelity detail. View-dependent lighting is managed through spherical harmonics, allowing color information to shift based on the camera angle.

The framework utilizes stochastic gradient descent to iteratively refine scene geometry and appearance by minimizing the difference between rendered outputs and ground truth images. This approach supports the development of digital models for spatial analysis and research in computer vision, while enabling real-time rendering of complex environments.

## Tags

### Artificial Intelligence & ML

- [Novel View Synthesis Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/image-synthesis-optimizers/novel-view-synthesis-engines.md) — Generates high-quality novel viewpoints from sparse image data using volumetric light field calculations. ([source](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/))
- [Reconstruction Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/computer-vision/reconstruction-tools.md) — Transforms two-dimensional photographs into photorealistic three-dimensional environments using optimized covariance and density parameters.
- [Adaptive Density Controllers](https://awesome-repositories.com/f/artificial-intelligence-ml/density-estimation/adaptive-density-controllers.md) — Manages scene complexity by dynamically splitting or pruning primitives to ensure high-fidelity detail.

### Graphics & Multimedia

- [3D Rendering Engines](https://awesome-repositories.com/f/graphics-multimedia/graphics-engines-rendering/scene-management-systems/3d-rendering-engines.md) — Provides a high-performance system for optimizing volumetric scene representations and synthesizing novel views in real-time.
- [3D Reconstruction Pipelines](https://awesome-repositories.com/f/graphics-multimedia/media-production-suites/animation-tools/mathematical-visualization-engines/3d-surface-visualizations/3d-reconstruction-pipelines.md) — Converts sets of two-dimensional photographs into accurate three-dimensional digital models for visualization and spatial analysis.
- [Radiance Field Engines](https://awesome-repositories.com/f/graphics-multimedia/radiance-field-engines.md) — Processes three-dimensional point clouds into differentiable Gaussian primitives for high-fidelity visual rendering.
- [Geometry Optimizers](https://awesome-repositories.com/f/graphics-multimedia/graphics-engines-rendering/scene-management-systems/geometry-optimizers.md) — Optimizes scene geometry by dynamically adjusting density and covariance to capture complex visual details. ([source](https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/))

### Scientific & Mathematical Computing

- [Differentiable Rasterizers](https://awesome-repositories.com/f/scientific-mathematical-computing/numerical-mathematical-foundations/computational-geometry/tiling-systems/differentiable-rasterizers.md) — Projects three-dimensional primitives into image space using a tile-based sorting approach that allows for efficient gradient-based optimization.

### Software Engineering & Architecture

- [Gaussian Point Representations](https://awesome-repositories.com/f/software-engineering-architecture/gaussian-grid-mapping/gaussian-point-representations.md) — Represents complex scenes as a collection of anisotropic three-dimensional Gaussians storing position, opacity, color, and covariance.

### User Interface & Experience

- [Spherical Harmonic Encoders](https://awesome-repositories.com/f/user-interface-experience/color-spaces/spherical-harmonic-encoders.md) — Models view-dependent lighting effects by storing color information as coefficients that change based on the viewing angle.