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

Descubre los mejores repositorios open-source con nuestra búsqueda potenciada por IA.

ExplorarBúsquedas curadasAlternativas open-sourceSoftware autohospedableBlogMapa del sitio
ProyectoServidor MCPAcerca deCómo clasificamosPrensa
Aviso legalPrivacidadTérminos
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
princeton-vl avatar

princeton-vl/infinigen

0
View on GitHub↗
7,022 estrellas·599 forks·Python·BSD-3-Clause·6 vistasinfinigen.org↗

Infinigen

Infinigen is a procedural 3D scene generation framework that creates photorealistic indoor and outdoor environments for computer vision training data. It combines constraint-based object placement, GPU geometry shaders, and ground-truth rendering passes to produce scenes with depth, normals, and segmentation masks alongside final images.

The framework distinguishes itself through modular asset composition, a node-graph material system, and physics simulation integration that embeds rigid-body and fluid dynamics directly into the generation pipeline. Procedural rule-based scene composition and deterministic random seed parameterization ensure reproducible, infinitely varied content without external textures or manual modeling.

Beyond scene generation, the toolset supports creating individual 3D assets, simulating physics and fluids, and exporting scenes to standard formats like OBJ and OpenUSD. This makes it a complete pipeline for producing supervised training data with ground-truth annotations for computer vision model development.

Features

  • Procedural Generators - Core capability: generates infinite photorealistic 3D scenes procedurally for computer vision training.
  • Procedural Scene Generators - Creates infinite photorealistic indoor and outdoor 3D scenes procedurally for computer vision training data.
  • Synthetic Training Data Generators - Produces photorealistic scenes with ground-truth annotations to support supervised model training.
  • Multi-Channel Render Passes - Renders depth, normals, and segmentation masks alongside final images for supervised training data.
  • Embedded Physics Solvers - Embeds rigid-body and fluid dynamics solvers directly into the generation pipeline for physically accurate interactions.
  • Random Number Generator Seeding - Controls all generation variability through a single random seed for deterministic reproducibility.
  • Rule-Based Layout Systems - Generates scenes by combining modular geometry, materials, and layouts using hand-authored procedural rules.
  • Procedural Geometry Shaders - Generates 3D geometry on the GPU using shader programs from mathematical functions and noise.
  • Node-Based Material Generation - Defines materials as interconnected nodes that compute surface properties procedurally without external textures.
  • Spatial Constraint Solvers - Solves spatial constraints and collision rules to position objects realistically in procedurally generated scenes.
  • Procedural Building Blocks - Builds complex objects and scenes by combining smaller procedural building blocks.
  • Scene Annotation Generators - Produces extended ground-truth data like depth, normals, and segmentation masks alongside generated scenes.
  • Procedural Asset Generators - Creates individual procedural 3D assets such as materials and objects for use in custom scenes.
  • Physics Simulation - Generates fluid simulations and articulated assets for physics-based training environments.
  • Fluid and Articulated Simulations - Generates fluid simulations and articulated simulation assets for physics-based training environments.
  • 3D Scene Exporters - Exports generated 3D scenes to standard formats like OBJ and OpenUSD for external use.
  • Fluid & Articulated Simulation Assets - Generates fluid simulations and articulated assets for physics-based training environments.
  • Procedural Asset Creation - Creates individual procedural 3D assets like materials and objects for use in custom scenes.

Historial de estrellas

Gráfico del historial de estrellas de princeton-vl/infinigenGráfico del historial de estrellas de princeton-vl/infinigen

Búsqueda con IA

Explora más repositorios increíbles

Describe lo que necesitas en lenguaje sencillo: la IA clasifica miles de proyectos open-source curados por relevancia.

Start searching with AI

Alternativas open-source a Infinigen

Proyectos open-source similares, clasificados según cuántas características comparten con Infinigen.
  • google-deepmind/mujoco_menagerieAvatar de google-deepmind

    google-deepmind/mujoco_menagerie

    3,055Ver en GitHub↗

    mujoco_menagerie is a curated library of physical robot specifications and XML model definitions designed for standardized dynamics and contact simulation. It provides a collection of high-quality robot model files for humanoids, quadrupeds, and manipulators, alongside detailed kinematic and inertial parameters used to reproduce real-world robot behavior in virtual environments. The project serves as a repository of robotics simulation assets and MJCF model definitions optimized for accuracy. It includes standardized model libraries specifically for bipedal, quadrupedal, and humanoid hardware

    Pythonmujocorobotics
    Ver en GitHub↗3,055
  • belval/textrecognitiondatageneratorAvatar de Belval

    Belval/TextRecognitionDataGenerator

    3,681Ver en GitHub↗

    TextRecognitionDataGenerator is a system for creating synthetic text images and character masks to train and test optical character recognition models. It functions as a dataset tool that generates artificial images by combining dictionary words with specific fonts and backgrounds to produce training sets for machine learning. The project includes a handwriting simulation engine that uses machine learning models to produce synthetic handwritten text. It also features a document degradation simulator that applies skew, blur, and distortion to images to mimic the visual quality of scanned physi

    Pythondatadatasetfake
    Ver en GitHub↗3,681
  • brianvoe/gofakeitAvatar de brianvoe

    brianvoe/gofakeit

    5,306Ver en GitHub↗

    gofakeit is a Go library for creating realistic synthetic datasets and populating Go structs with mock information. It functions as a deterministic data generator, allowing for seedable random number generation to ensure reproducible datasets for software testing. The project distinguishes itself by providing a mock data API server that exposes generation functions as HTTP endpoints and a synthetic dataset exporter for producing files in CSV, JSON, and XML formats. It also includes a command-line interface for generating mock data directly from the terminal. The library covers a wide array o

    Godatafakegenerator
    Ver en GitHub↗5,306
  • armory3d/armortoolsAvatar de armory3d

    armory3d/armortools

    3,933Ver en GitHub↗

    Armortools is a 3D PBR texture painting suite and mesh texture workflow tool. It provides a system for painting physically based rendering materials directly onto 3D meshes using a combination of layer and mask support, a GPU-accelerated texture baker for extracting geometry data from high-polygon models, and a node-based material editor for creating procedural textures. The software features integrated neural network tools for AI texture authoring, allowing the generation of PBR maps from text prompts, image-based material extraction, and texture upscaling via local nodes. It also implements

    C3darmorpaintpainting
    Ver en GitHub↗3,933
Ver las 30 alternativas a Infinigen→

Preguntas frecuentes

¿Qué hace princeton-vl/infinigen?

Infinigen is a procedural 3D scene generation framework that creates photorealistic indoor and outdoor environments for computer vision training data. It combines constraint-based object placement, GPU geometry shaders, and ground-truth rendering passes to produce scenes with depth, normals, and segmentation masks alongside final images.

¿Cuáles son las características principales de princeton-vl/infinigen?

Las características principales de princeton-vl/infinigen son: Procedural Generators, Procedural Scene Generators, Synthetic Training Data Generators, Multi-Channel Render Passes, Embedded Physics Solvers, Random Number Generator Seeding, Rule-Based Layout Systems, Procedural Geometry Shaders.

¿Qué alternativas de código abierto existen para princeton-vl/infinigen?

Las alternativas de código abierto para princeton-vl/infinigen incluyen: google-deepmind/mujoco_menagerie — mujoco_menagerie is a curated library of physical robot specifications and XML model definitions designed for… belval/textrecognitiondatagenerator — TextRecognitionDataGenerator is a system for creating synthetic text images and character masks to train and test… carson-katri/dream-textures — Dream Textures is a Stable Diffusion integration for Blender that provides tools for text-to-image generation, depth… armory3d/armortools — Armortools is a 3D PBR texture painting suite and mesh texture workflow tool. It provides a system for painting… brianvoe/gofakeit — gofakeit is a Go library for creating realistic synthetic datasets and populating Go structs with mock information. It… chancejs/chancejs — Chance is a JavaScript library for generating random data, designed to produce realistic test data for automated tests…