awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
ArthurBrussee avatar

ArthurBrussee/brush

0
View on GitHub↗
3,685 stars·189 forks·Rust·apache-2.0·28 views

Brush

Brush is a tool for creating high-fidelity three-dimensional scene reconstructions from posed images using Gaussian splatting. It processes photographs with known camera coordinates to generate spatial geometry.

The project includes capabilities for refining reconstructions through 3D scene masking, which allows for the exclusion of specific image regions or the incorporation of transparency during the training process.

The system provides a command line interface for managing the training pipeline and debugging workflows. Visualization is handled via client-side WebGL rendering, which supports the display of static or animated scenes through compressed archive streaming.

Features

  • Gaussian Splatting Reconstruction - Provides a high-fidelity reconstruction of 3D environments from posed images using Gaussian splatting.
  • Gaussian Splatting Rasterizers - Renders 3D scenes by projecting point-based clouds of colored ellipsoids onto a 2D image plane.
  • Reconstruction Weighting - Adjusts the influence of specific image pixels during reconstruction to ignore unwanted regions.
  • Gaussian Splat Rendering - Displays static or animated 3D scenes using various formats, including streaming links and compressed archives.
  • Reconstruction Masking - Allows for refining 3D reconstructions by excluding specific image regions or incorporating transparency during training.
  • Training Data Masking - Removes unwanted objects or refines specific regions by masking training data during reconstruction.
  • Client Side Rendering - Implements local pixel color calculation in the browser via WebGL for interactive viewing of spatial data.
  • Spatial Data Processing - Calculates spatial geometry by matching features across multiple photographs with known camera coordinates.
  • CLI Training Toolkits - Provides a command-line utility to manage the sequence of data ingestion and optimization for scene training.
  • Command Line Interfaces - Ships a terminal-based interface to execute 3D reconstruction and rendering tasks.
  • Splat Data Streaming - Loads high-density point clouds by fetching compressed serialized scene data over a network.

Star history

Star history chart for arthurbrussee/brushStar history chart for arthurbrussee/brush

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Projects sharing features with Brush

These projects share indexed features with Brush. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • viser-project/viserviser-project avatar

    viser-project/viser

    2,633View on GitHub↗

    Viser is a Python 3D visualization framework and remote scene server that renders 3D primitives, point clouds, and meshes in a web browser. It functions as a server-client system that synchronizes scene state and camera poses to a web client via WebSockets. The framework provides specialized capabilities for robotics and computer vision, including a URDF robot visualizer for loading robot models and joint states, as well as a GPU-accelerated Gaussian splatting viewer for high-fidelity volumetric rendering. It also supports the visualization of human body models and skinned meshes for pose ana

    Pythonpythonvisualizationweb
    View on GitHub↗2,633
  • mathewsachin/capturaMathewSachin avatar

    MathewSachin/Captura

    10,731View on GitHub↗

    Captura is a desktop screen recording and screenshot utility designed to capture video, webcam feeds, and system audio into multimedia recordings. It functions as a recording suite that can also be operated as a command line video recorder, allowing users to trigger and manage capture workflows via terminal commands. The software distinguishes itself by recording user input, such as mouse movements and keystrokes, as visual overlays on top of the captured video. It further supports automated workflows through the integration of system-level hardware media keys, enabling recording state change

    C#
    View on GitHub↗10,731
  • antimatter15/splatantimatter15 avatar

    antimatter15/splat

    2,890View on GitHub↗

    Splat is a browser-based 3D Gaussian splatting viewer that renders photorealistic scenes from photographs directly in a web browser. It uses WebGL 2.0 compute shaders to perform per-splat sorting and alpha blending on the GPU, enabling real-time display of millions of semi-transparent ellipsoids. The application also functions as a drag-and-drop converter that transforms .ply files from 3D Gaussian splatting software into the optimized .splat format for web rendering. The viewer provides full camera navigation through keyboard, mouse, and touch gestures, and includes a camera view manager tha

    JavaScript
    View on GitHub↗2,890
  • facebook/reactfacebook avatar

    facebook/react

    245,669View on GitHub↗

    React is a JavaScript library for building user interfaces based on a component-driven architecture and unidirectional data flow.

    JavaScriptjavascriptuifrontend
    View on GitHub↗245,669
Compare all 30 related projects→

Frequently asked questions

What does arthurbrussee/brush do?

Brush is a tool for creating high-fidelity three-dimensional scene reconstructions from posed images using Gaussian splatting. It processes photographs with known camera coordinates to generate spatial geometry.

What are the main features of arthurbrussee/brush?

The main features of arthurbrussee/brush are: Gaussian Splatting Reconstruction, Gaussian Splatting Rasterizers, Reconstruction Weighting, Gaussian Splat Rendering, Reconstruction Masking, Training Data Masking, Client Side Rendering, Spatial Data Processing.

Which projects share features with arthurbrussee/brush?

Projects with overlapping indexed features include: viser-project/viser — Viser is a Python 3D visualization framework and remote scene server that renders 3D primitives, point clouds, and… mathewsachin/captura — Captura is a desktop screen recording and screenshot utility designed to capture video, webcam feeds, and system audio… antimatter15/splat — Splat is a browser-based 3D Gaussian splatting viewer that renders photorealistic scenes from photographs directly in… facebook/react — React is a JavaScript library for building user interfaces based on a component-driven architecture and unidirectional… qgis/qgis — QGIS is a professional, open-source desktop geographic information system designed for the creation, editing,… esoolgnah/frontend-interview-questions — Frontend-Interview-Questions is an educational knowledge base and study guide designed for technical interview…