Open-source graphics software
2502 open-source libraries, tools and applications tagged graphics, ranked by how closely graphics is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
2502 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| dcharatan/pixelsplat pixelSplat is a PyTorch implementation of a feed-forward model that reconstructs 3D radiance fields parameterized by 3D Gaussian primitives… | 27 | 1282 | stable |
| Stable-X/Stable3DGen Stable3DGen is a modular Python framework for generating 3D assets from images, adapted from Microsoft's TRELLIS with NVIDIA library depend… | 30 | 1278 | active |
| DCurrent/openbor OpenBOR is a royalty-free, sprite-based 2D side-scrolling game engine optimized for beat 'em ups (Double Dragon, Streets of Rage, Final Fig… | 66 | 1273 | active |
| ToniRV/NeRF-SLAM NeRF-SLAM is a real-time dense monocular SLAM system that combines neural radiance fields (Instant-NGP) with probabilistic volumetric fusio… | 32 | 1266 | active |
| cvg/depthsplat DepthSplat is a PyTorch research library implementing a CVPR 2025 model that connects Gaussian splatting with single/multi-view depth estim… | 53 | 1262 | active |
| Fictionarry/ER-NeRF ER-NeRF is the official PyTorch implementation of an ICCV 2023 paper on region-aware Neural Radiance Fields for high-fidelity talking portr… | 21 | 1259 | stable |
| nv-tlabs/GET3D GET3D is NVIDIA's PyTorch implementation of a generative model that synthesizes high-quality 3D textured meshes (cars, chairs, animals, bui… | 32 | 4433 | maintenance |
| Roblox/cube Cube is Roblox's open-source family of foundation models for 3D intelligence, including text-to-3D shape generation and part-controllable m… | 55 | 1256 | active |
| 3DTopia/OpenLRM OpenLRM is an open-source PyTorch implementation of Large Reconstruction Models (LRM) that reconstruct 3D objects (meshes and rendered vide… | 18 | 1250 | active |
| b-editor/beutl Beutl is a free, open-source, cross-platform video editing and compositing application built on .NET. It offers a timeline with layers, nod… | 99 | 1242 | active |
| Myriad-Dreamin/typst.ts Typst.ts brings the Typst typesetting engine to JavaScript environments via WebAssembly, providing a Typst World implementation plus export… | 87 | 1222 | active |
| dartsim/dart DART (Dynamic Animation and Robotics Toolkit) is an open-source, research-focused C++ physics engine for robotics, animation, and machine l… | 100 | 1217 | active |
| Tencent-Hunyuan/HunyuanWorld-Mirror HunyuanWorld-Mirror is a feed-forward 3D reconstruction model from Tencent that predicts camera poses, intrinsics, depth maps, point clouds… | 52 | 1210 | active |
| networked-aframe/networked-aframe Networked-Aframe is a JavaScript framework built on A-Frame for creating multi-user virtual reality experiences on the web using HTML and J… | 86 | 1207 | active |
| sleepy-zone/fabritor-web Fabritor is an open-source creative image editor built on fabric.js and React, designed to let developers quickly build their own image edi… | 28 | 1199 | active |
| chensjtu/GaussianObject GaussianObject is a research framework for high-quality 3D object reconstruction from as few as four input images using Gaussian splatting,… | 26 | 1192 | active |
| fand/vfx-js VFX-JS is a JavaScript/TypeScript library for adding WebGL-powered visual effects to websites. It attaches GLSL shader effects to normal HT… | 90 | 1153 | active |
| etro-js/etro Etro is a framework-agnostic TypeScript library for programmatically editing videos in the browser. It composites video, audio, image, and … | 92 | 1151 | active |
| PSn00bSDK PSn00bSDK is an open source homebrew software development kit for the original Sony PlayStation, providing a GCC-based C/C++ toolchain, lib… | 23 | 1142 | active |
| kzampog/cilantro cilantro is a lean, templated C++ library for processing 3D point cloud data, offering kd-trees, normal estimation, resampling, PCA, PLY I/… | 41 | 1138 | active |
| Xilinx/Vitis_Libraries A collection of open-source, performance-optimized accelerated libraries for the AMD Vitis Unified Software Platform, offering out-of-the-b… | 90 | 1130 | active |
| princeton-vl/DPVO DPVO is a deep learning-based visual odometry and SLAM system that estimates camera trajectories from video or image sequences using patch-… | 75 | 1127 | active |
| fschutt/printpdf printpdf is a Rust library (also usable via WASM) for creating, reading, writing, and rendering PDF documents. It supports pages, layers, g… | 67 | 1125 | active |
| 1j01/textual-paint Textual Paint is a terminal-based (TUI) image editor that recreates the classic MS Paint interface, built with the Textual framework in Pyt… | 58 | 1121 | active |
| BabylonJS/Editor A free, open-source desktop visual editor for creating and editing 3D scenes and games with the Babylon.js engine, available on Windows, ma… | 99 | 1118 | active |
| freebasic/fbc FreeBASIC (fbc) is a free, open-source, self-hosting multi-platform BASIC compiler with syntax similar to MS-QuickBASIC, adding modern feat… | 53 | 1117 | active |
| OpenKinect/libfreenect libfreenect is a userspace driver and library for the original Microsoft Xbox Kinect sensor, providing access to RGB and depth images, moto… | 23 | 3838 | maintenance |
| szymanowiczs/splatter-image Official PyTorch implementation of 'Splatter Image: Ultra-Fast Single-View 3D Reconstruction' (CVPR 2024), which uses an image-to-image net… | 27 | 1111 | active |
| vinc/moros MOROS is a text-based hobby operating system written in Rust for x86-64 BIOS computers, inspired by Unix, Plan 9, and DOS. It includes a cu… | 81 | 1101 | active |
| lizhe00/AnimatableGaussians Official PyTorch implementation of the CVPR 2024 paper 'Animatable Gaussians', which learns pose-dependent Gaussian maps for high-fidelity … | 27 | 1099 | active |
| minghanqin/LangSplat Official implementation of LangSplat, a CVPR 2024 Highlight paper that constructs a 3D language field using 3D Gaussian Splatting with CLIP… | 44 | 1096 | active |
| zju3dv/InfiniDepth InfiniDepth is a CVPR 2026 research library for monocular depth estimation that represents depth as neural implicit fields, allowing depth … | 59 | 1089 | active |
| yerfor/Real3DPortrait Official PyTorch implementation of Real3D-Portrait, an ICLR 2024 Spotlight paper for one-shot realistic 3D talking portrait synthesis. It g… | 26 | 1087 | active |
| alibaba/LuaViewSDK LuaViewSDK is a cross-platform framework from Alibaba that builds native, dynamic user interfaces on iOS and Android using a single Lua scr… | 23 | 3725 | maintenance |
| abizovnuralem/go2_omniverse A Python library providing Unitree Go2 and G1 robot support for NVIDIA Isaac Lab / Isaac Sim, enabling simulation of these quadruped and hu… | 53 | 1080 | active |
| LAM LAM is a PyTorch implementation of a Large Avatar Model that reconstructs an animatable 3D Gaussian head from a single image in one forward… | 55 | 1070 | active |
| lkeab/gaussian-grouping Gaussian Grouping extends 3D Gaussian Splatting to jointly reconstruct and segment open-world 3D scenes by lifting 2D SAM masks into per-Ga… | 27 | 1064 | stable |
| YYC572652645/QCoolPage A collection of custom Qt widgets for building visually striking desktop interfaces, including carousels, bar charts, progress bars, panels… | 67 | 1056 | active |
| J-x-Z/cocoa-way Cocoa-Way is a native macOS Wayland compositor written in Rust that renders Linux desktop applications using Apple's Metal API. It acts as … | 79 | 1052 | active |
| 3DTopia/3DTopia-XL 3DTopia-XL is a 3D diffusion transformer model that generates high-quality 3D assets with PBR materials from a single image or text prompt … | 34 | 1047 | active |
| vpinball/vpinball Visual Pinball is an open-source pinball table editor and physics simulator written in C++. It lets users build, edit, and play virtual pin… | 79 | 1041 | active |
| jackyzha0/sunlit A pure CSS implementation of sunlight streaming through window blinds, using layered divs, progressive backdrop-filter blur, and SVG feTurb… | 22 | 1040 | active |
| MeshAnything MeshAnything is an autoregressive transformer model that generates artist-created 3D meshes (up to 1600 faces in V2) aligned with a given s… | 28 | 1023 | active |
| maximeraafat/BlenderNeRF BlenderNeRF is a Blender add-on that generates synthetic NeRF and Gaussian Splatting datasets with a single click, exporting renders and ca… | 23 | 1019 | active |
| NVlabs/eg3d Official PyTorch implementation of EG3D, an efficient geometry-aware 3D generative adversarial network from NVIDIA Research (CVPR 2022). It… | 32 | 3336 | maintenance |
| aserbao/AndroidCamera An Android library and demo app implementing a TikTok-style custom camera with video and audio editing features such as segment recording, … | 23 | 3294 | maintenance |
| Habitat AI Habitat is a high-performance, physics-enabled 3D simulation platform for Embodied AI research, consisting of Habitat-Sim (a fast 3D sim… | 68 | 3159 | maintenance |
| CainKernel/CainCamera An open-source Android app and set of libraries demonstrating how to build a beauty camera, image editor, and short-video editor. It implem… | 32 | 2966 | maintenance |
| ethz-asl/maplab maplab 2.0 is an open, research-oriented C++ mapping framework for multi-session and multi-robot SLAM, built on ROS. It provides robust vis… | 23 | 2880 | maintenance |
| icexin/eggos Eggos is a unikernel written almost entirely in Go that runs Go applications directly on x86 bare metal, supporting Go features like GC, go… | 23 | 2328 | maintenance |
| zju3dv/NeuralRecon NeuralRecon is a deep learning framework for real-time 3D scene reconstruction from monocular video with known camera poses. It reconstruct… | 32 | 2284 | maintenance |
| OpenKinect/libfreenect2 libfreenect2 is an open-source C++ driver library for the Kinect for Windows v2 depth camera. It handles RGB, IR, and depth image transfer … | 23 | 2254 | maintenance |
| magenta/magenta-js Magenta.js is a collection of TypeScript libraries for running inference with pre-trained Magenta machine learning models directly in the b… | 68 | 2133 | maintenance |
| junshutang/Make-It-3D Make-It-3D is a research codebase from an ICCV 2023 paper that creates high-fidelity 3D content from a single image using a 2D diffusion mo… | 31 | 1898 | maintenance |
| magicleap/Atlas Atlas is a PyTorch-based deep learning model from Magic Leap that performs end-to-end 3D scene reconstruction from posed RGB images, produc… | 32 | 1859 | maintenance |
| LingBot-World LingBot-World is an open-source world model that generates high-fidelity, interactive simulated environments from video generation, support… | 56 | 1823 | maintenance |
| shunsukesaito/PIFu PyTorch implementation of PIFu (Pixel-Aligned Implicit Function), a deep learning method that reconstructs high-resolution 3D surfaces and … | 32 | 1817 | maintenance |
| Cleveroad/WaveInApp WaveInApp is an Android library providing an audio visualization view with a wave effect, rendering live audio from players, streams, or sp… | 32 | 1792 | maintenance |
| nywang16/Pixel2Mesh Pixel2Mesh is the official TensorFlow implementation of the ECCV 2018 paper that generates 3D mesh models from a single RGB image using a g… | 32 | 1768 | maintenance |
| DeepMotionEditing/deep-motion-editing A PyTorch-based end-to-end library for editing and rendering 3D character motion, built on SIGGRAPH 2020 research. It provides deep learnin… | 32 | 1726 | maintenance |
| dunbar12138/pix2pix3D pix2pix3D is the official PyTorch implementation of a CVPR 2023 paper on 3D-aware conditional image synthesis. It generates 3D objects (neu… | 31 | 1717 | maintenance |
| Fyusion/LLFF LLFF (Local Light Field Fusion) is a TensorFlow implementation of the SIGGRAPH 2019 paper for novel view synthesis from sparse input images… | 32 | 1708 | maintenance |
| zhan-xu/RigNet RigNet is a PyTorch implementation of the SIGGRAPH 2020 paper on neural rigging for articulated 3D characters. It takes a character mesh as… | 32 | 1520 | maintenance |
| PlenOctrees Official PyTorch implementation of pixelNeRF, a CVPR 2021 method that predicts neural radiance fields conditioned on one or few input image… | 32 | 1465 | maintenance |
| uzh-rpg/flightmare Flightmare is a modular quadrotor simulator from the UZH Robotics and Perception Group, composed of a decoupled Unity-based rendering engin… | 23 | 1424 | maintenance |
| supermedium/superframe Superframe is a curated collection of components for A-Frame, the web framework for building VR experiences. It includes components for ani… | 66 | 1412 | maintenance |
| OpenNI/OpenNI OpenNI is a C++ framework and SDK providing a standard interface for depth sensors and 3D vision devices like PrimeSense and Kinect cameras… | 32 | 1395 | maintenance |
| MoyGcc/vid2avatar Vid2Avatar is the official PyTorch implementation of a CVPR 2023 method that reconstructs detailed 3D human avatars from monocular in-the-w… | 54 | 1361 | maintenance |
| dorarad/gansformer GANformer is a research implementation of a generative adversarial transformer that uses a bipartite attention structure for efficient high… | 23 | 1344 | maintenance |
| EricGuo5513/momask-codes Official PyTorch implementation of MoMask (CVPR 2024), a masked modeling framework that generates 3D human motion sequences from text promp… | 27 | 1330 | maintenance |
| google/sg2im A PyTorch research implementation of the CVPR 2018 paper 'Image Generation from Scene Graphs' by Johnson et al. It converts a structured sc… | 10 | 1325 | maintenance |
| aitorzip/PyTorch-CycleGAN A clean, readable PyTorch implementation of CycleGAN for unpaired image-to-image translation using cycle-consistent adversarial networks. I… | 32 | 1321 | maintenance |
| NVlabs/alias-free-gan The official project page and code for Alias-Free GAN, an NVIDIA research method for aliasing-free generative adversarial networks. The imp… | 32 | 1287 | maintenance |
| apple/ml-neuman Official reference implementation of NeuMan (ECCV 2022), which reconstructs an animatable human and the background scene from a single vide… | 75 | 1285 | maintenance |
| scijs/ndarray A JavaScript library providing modular multidimensional array views over 1D typed arrays, similar to numpy arrays. It supports constant-tim… | 73 | 1245 | maintenance |
| autonomousvision/giraffe Official PyTorch implementation of GIRAFFE, a CVPR 2021 (oral, best paper award) generative model that represents scenes as compositional g… | 32 | 1238 | maintenance |
| facebookresearch/House3D House3D is a virtual 3D environment of over 45k fully annotated indoor scenes from the SUNCG dataset, built for training embodied AI agents… | 10 | 1199 | maintenance |
| Xharlie/pointnerf Point-NeRF is a research implementation of a point-based neural radiance field method (CVPR 2022 Oral) that models scenes with neural 3D po… | 32 | 1154 | maintenance |
| Jannchie/anichart.js A TypeScript library for creating animated data visualization videos, rendering charts like bar chart races, line, pie, and map charts via … | 23 | 1129 | maintenance |
| ethz-asl/segmap SegMap is a C++ library and ROS package providing a segment-based 3D map representation for robot localization, environment reconstruction,… | 32 | 1096 | maintenance |
| YudongGuo/AD-NeRF A PyTorch implementation of AD-NeRF, an ICCV 2021 paper that synthesizes talking-head videos by driving neural radiance fields with audio i… | 32 | 1073 | maintenance |
| keijiro/Pix2Pix A Unity library that runs pix2pix image-to-image translation neural networks in real time using compute shaders. It includes its own infere… | 23 | 1037 | maintenance |
| snap-research/NeROIC Official PyTorch implementation of NeROIC, a neural method for capturing 3D object geometry and material from online image collections and … | 32 | 1012 | maintenance |
| rexdex/recompiler A C++ tool that converts Xbox 360 PowerPC executables into native Windows x86 executables, handling CPU translation, endianness, and GPU em… | 32 | 1742 | experimental |
| VoidmatrixHeathcliff/VoidNovelEngine VoidNovelEngine is a free, open-source engine for building visual novels and narrative games using a flowchart-style node editor instead of… | 65 | 1688 | experimental |
| Anything-of-anything/Anything-3D Anything-3D is a Python research project that combines Meta's Segment Anything model with a series of 3D models (3DFuse, Zero 1-to-3, NeRF,… | 30 | 1633 | experimental |
| lizhihao6/Sparc3D Sparc3D is the official implementation of a research framework for high-resolution 3D shape modeling, combining a sparse deformable marchin… | 28 | 1359 | experimental |
| Tencent-Hunyuan/Hunyuan3D-WorldClaw WorldClaw is a research framework from Tencent Hunyuan for agentic, large-scale 3D open-world generation, released alongside an arXiv paper… | 53 | 1334 | experimental |
| maximecb/noisecraft NoiseCraft is a browser-based visual programming language and platform for sound synthesis and music making, inspired by PureData and Max/M… | 75 | 1228 | experimental |
| ffwff/lilith Lilith is a hobby x86-64 operating system with a POSIX-like kernel and userspace written in Crystal. It includes a garbage collector, FAT16… | 23 | 1171 | experimental |
| gammasoft71/xtd xtd is a modern C++20 open-source framework for building console (CLI), forms-based GUI, and unit test applications and libraries across ma… | 67 | 1167 | experimental |
| danfragoso/thdwb THDWB (The Hotdog Web Browser) is a web browser with its own layout and rendering engine, HTML/CSS parsers, and UI toolkit, written from sc… | 32 | 1140 | experimental |
| facebookresearch/AnimatedDrawings A Python tool from Meta AI that automatically animates children's drawings of human figures, implementing the algorithm from the paper 'A M… | 10 | 12808 | abandoned |
| linebender/druid Druid is a data-first, Rust-native UI toolkit for building cross-platform desktop applications, inspired by declarative frameworks like Flu… | 54 | 9699 | abandoned |
| SeriousCache/UABE UABE (Asset Bundle Extractor) is a Windows desktop editor for Unity .assets and AssetBundle files, supporting export/import of textures, te… | 10 | 4138 | abandoned |
| ericdrowell/KineticJS KineticJS is an HTML5 Canvas JavaScript framework that extends the 2d context with a scene graph, enabling canvas interactivity for desktop… | 23 | 4011 | abandoned |
| xbpeng/DeepMimic DeepMimic is a C++ simulation framework with a Python (SWIG/TensorFlow) wrapper that trains simulated humanoid characters to imitate motion… | 53 | 3110 | abandoned |
| LaiFeng-Android/SopCastComponent SopCastComponent is a pure-Java Android live-streaming SDK covering capture, audio/video processing, encoding, and RTMP upload with FLV mux… | 32 | 2457 | abandoned |
| gak/pycallgraph pycallgraph is a Python module that generates call graph visualizations for Python programs, usable from the command line or as an imported… | 10 | 1858 | abandoned |
| Famous Engine Famous is a JavaScript rendering and animation engine for building high-performance, GPU-accelerated web interfaces. This repository is dep… | 32 | 1745 | abandoned |