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
EmbarkStudios avatar

EmbarkStudios/kajiyaArchived

0
View on GitHub↗
5,334 stars·204 forks·Rust·Apache-2.0·28 views

Kajiya

Kajiya is a physically based rendering engine and real-time global illumination renderer. It utilizes a GPU-accelerated path tracer to simulate real-world material properties, such as roughness and metalness, to achieve photorealistic visual results.

The engine incorporates a temporal super-resolution upscaler to increase final render resolution by reconstructing images from lower-resolution internal frames. It also generates high-fidelity reference images through path-tracing to verify the visual accuracy of real-time lighting outputs.

The system covers 3D scene visualization and asset management, including the import of meshes and scene configurations. It further supports image-based lighting using high-dynamic range images to provide realistic ambient environmental illumination.

Features

  • Physically Based Rendering - A physically based rendering engine that simulates real-world material properties for photorealistic results.
  • Physically Based Rendering Materials - Models surface light interactions using roughness and metalness mathematical models for photorealistic materials.
  • Indirect Lighting Simulation - Simulates realistic indirect lighting and light bounces in dynamic scenes using ray-tracing and compute shaders.
  • GPU-Accelerated Path Tracers - Ships a GPU-accelerated path tracer to simulate individual light paths for high-fidelity reference images.
  • Compute Shader Implementations - Uses GPU-accelerated compute shaders to perform massively parallel ray intersection tests for global illumination.
  • Real-Time Raytracing - Implements real-time global illumination using ray-tracing and compute shaders to simulate light bounces and soft shadows.
  • Real-Time Super-Resolution - Maintains rendering performance by using real-time temporal super-resolution to upscale internal frames.
  • 3D Scene Visualization - Allows previewing how 3D assets appear under physically accurate lighting conditions.
  • Image-Based Lighting - Provides realistic ambient environmental illumination by utilizing high-dynamic range image maps as light sources.
  • Reference Synthesis - Produces accurate reference images through path-tracing to verify real-time render quality.
  • Reference Rendering - Generates high-fidelity reference images via path-tracing to verify the accuracy of real-time outputs.
  • Reference Image Generation - Generates high-fidelity path-traced reference images to verify the visual accuracy of real-time lighting outputs.
  • Temporal Super-Resolution Upscalers - A performance tool that increases final render resolution by reconstructing images from lower-resolution internal frames.

Star history

Star history chart for embarkstudios/kajiyaStar history chart for embarkstudios/kajiya

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

Frequently asked questions

What does embarkstudios/kajiya do?

Kajiya is a physically based rendering engine and real-time global illumination renderer. It utilizes a GPU-accelerated path tracer to simulate real-world material properties, such as roughness and metalness, to achieve photorealistic visual results.

What are the main features of embarkstudios/kajiya?

The main features of embarkstudios/kajiya are: Physically Based Rendering, Physically Based Rendering Materials, Indirect Lighting Simulation, GPU-Accelerated Path Tracers, Compute Shader Implementations, Real-Time Raytracing, Real-Time Super-Resolution, 3D Scene Visualization.

Which projects share features with embarkstudios/kajiya?

Projects with overlapping indexed features include: erichlof/three.js-pathtracing-renderer — This project is a browser-based, physically based path-tracing renderer built on WebGL and integrated with Three.js.… o3de/o3de — This project is an open-source 3D game engine designed for building high-fidelity games, simulations, and cinematic… microsoft/trellis.2 — TRELLIS.2 is a generative image-to-3D system that creates high-resolution 3D assets with physically based rendering… raytracing/raytracing.github.io — This project is a ray tracing reference implementation and educational resource for building a Monte Carlo path tracer… openmoonray/openmoonray — OpenMoonray is a production-grade physically based rendering system and path-tracing engine. It simulates the physical… godotengine/godot-demo-projects — This repository is a comprehensive collection of functional 2D and 3D demo projects and implementation samples for the…

Projects sharing features with Kajiya

These projects share indexed features with Kajiya. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • erichlof/three.js-pathtracing-renderererichlof avatar

    erichlof/THREE.js-PathTracing-Renderer

    2,216View on GitHub↗

    This project is a browser-based, physically based path-tracing renderer built on WebGL and integrated with Three.js. It functions as a real-time global illumination engine, calculating light bouncing, soft shadows, reflections, refractions, and color bleeding interactively within web environments. The rendering system incorporates progressive multi-pass accumulation to refine noisy images iteratively over multiple frames, alongside GPU-accelerated spatial acceleration structures and bounding volume hierarchies to handle complex geometry. It supports diverse material types such as refractive

    GLSLglobal-illuminationpathpath-tracer
    View on GitHub↗2,216
  • o3de/o3deo3de avatar

    o3de/o3de

    8,954View on GitHub↗

    This project is an open-source 3D game engine designed for building high-fidelity games, simulations, and cinematic environments. It functions as a robotics simulation platform with native integration for ROS 2 to model robot controllers and sensors. The engine features a multi-threaded Forward+ physically based renderer that supports hardware-accelerated ray tracing and global illumination. The system is built on a modular extension architecture using Gems to add or replace features without modifying core binaries. It includes a native SDK for AWS cloud integration, enabling IAM authenticati

    C++3d-graphics3d-graphics-engineanimation
    View on GitHub↗8,954
  • microsoft/trellis.2microsoft avatar

    microsoft/TRELLIS.2

    3,910View on GitHub↗

    TRELLIS.2 is a generative image-to-3D system that creates high-resolution 3D assets with physically based rendering materials from 2D images. It utilizes a sparse voxel representation to handle complex topologies and internal structures without relying on iso-surface fields. The project features a structured latent space representation that maps geometry and texture attributes to maintain visual fidelity. It employs an optimization-free geometry reconstruction process to decode latent representations directly into voxel grids and includes a PBR texture generator for synthesizing base color, r

    Python
    View on GitHub↗3,910
  • raytracing/raytracing.github.ioRayTracing avatar

    RayTracing/raytracing.github.io

    10,174View on GitHub↗

    This project is a ray tracing reference implementation and educational resource for building a Monte Carlo path tracer from scratch. It serves as a guide for physically based rendering, demonstrating how to simulate the behavior of light and materials to create realistic images. The implementation includes a spatial hierarchy accelerator to optimize intersection tests and a system for generating images in the portable pixmap format. It provides a community reference library of implementations across various programming languages and distributes complete source code archives for study. The pr

    HTMLbookgraphics-renderingmarkdeep
    View on GitHub↗10,174
  • Compare all 30 related projects→