Showing 1983 open source projects for "3d from 2d"

View related business solutions
  • MongoDB Atlas runs apps anywhere Icon
    MongoDB Atlas runs apps anywhere

    Deploy in 115+ regions with the modern database for every enterprise.

    MongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
    Start Free
  • Build Securely on AWS with Proven Frameworks Icon
    Build Securely on AWS with Proven Frameworks

    Lay a foundation for success with Tested Reference Architectures developed by Fortinet’s experts. Learn more in this white paper.

    Moving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
    Download Now
  • 1
    InsightFace

    InsightFace

    State-of-the-art 2D and 3D Face Analysis Project

    State-of-the-art deep face analysis library. InsightFace is an open-source 2D&3D deep face analysis library. InsightFace is an integrated Python library for 2D&3D face analysis. InsightFace efficiently implements a wide variety of state-of-the-art algorithms for face recognition, face detection, and face alignment, which are optimized for both training and deployment. Research institutes and industrial organizations can get benefits from InsightFace library.
    Downloads: 501 This Week
    Last Update:
    See Project
  • 2
    SAM 3D Objects

    SAM 3D Objects

    Models for object and human mesh reconstruction

    SAM 3D Objects is a foundation model that reconstructs full 3D geometry, texture, and spatial layout of objects and scenes from a single image. Given one RGB image and object masks (for example, from the Segment Anything family), it can generate a textured 3D mesh for each object, including pose and approximate scene layout. The model is specifically designed to be robust in real-world images with clutter, occlusions, small objects, and unusual viewpoints, where many earlier 3D-from-image systems struggle. ...
    Downloads: 9 This Week
    Last Update:
    See Project
  • 3
    Step1X-3D

    Step1X-3D

    High-Fidelity and Controllable Generation of Textured 3D Assets

    ...The result is fully 3D assets — meshes + textures — which can be rendered from any viewpoint, textured consistently, and used in 3D applications. To achieve this, the project includes a massive curated dataset: among more than 5 million candidate 3D assets, it filters and standardizes to produce a high-quality 2 million–asset subset suitable for training.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 4
    Mesh R-CNN

    Mesh R-CNN

    code for Mesh R-CNN, ICCV 2019

    Mesh R-CNN is a 3D reconstruction and object understanding framework developed by Facebook Research that extends Mask R-CNN into the 3D domain. Built on top of Detectron2 and PyTorch3D, Mesh R-CNN enables end-to-end 3D mesh prediction directly from single RGB images. The model learns to detect, segment, and reconstruct detailed 3D mesh representations of objects in natural images, bridging the gap between 2D perception and 3D understanding. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • Go From AI Idea to AI App Fast Icon
    Go From AI Idea to AI App Fast

    One platform to build, fine-tune, and deploy ML models. No MLOps team required.

    Access Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
    Try Free
  • 5
    Point Cloud Library

    Point Cloud Library

    A standalone, large scale, open project for 2D/3D image processing

    The Point Cloud Library (PCL) is a standalone, large scale, open project for 2D/3D image and point cloud processing. PCL is released under the terms of the BSD license, and thus free for commercial and research use. Whether you’ve just discovered PCL or you’re a long time veteran, this page contains links to a set of resources that will help consolidate your knowledge on PCL and 3D processing. An additional Wiki resource for developers is available too.
    Downloads: 24 This Week
    Last Update:
    See Project
  • 6
    MESHROOM

    MESHROOM

    3D reconstruction software

    Photogrammetry is the science of making measurements from photographs. It infers the geometry of a scene from a set of unordered photographies or videos. Photography is the projection of a 3D scene onto a 2D plane, losing depth information. The goal of photogrammetry is to reverse this process. The dense modeling of the scene is the result yielded by chaining two computer vision-based pipelines, “Structure-from-Motion” (SfM) and “Multi View Stereo” (MVS). ...
    Downloads: 116 This Week
    Last Update:
    See Project
  • 7
    Lumos Engine

    Lumos Engine

    Cross-Platform C++ 2D/3D game engine

    Cross-platform 2D and 3D Game Engine written in C++ that supports both OpenGL and Vulkan. Support for Windows, Linux, macOS. Support for OpenGL/Vulkan. D audio using OpenAL. Rendering 3D models with PBR shading. Debug gui using ImGui 3D collision detection - cuboid/sphere/pyramid. 2D collision detection - Box2D. Basic lua scripting support.
    Downloads: 7 This Week
    Last Update:
    See Project
  • 8
    SAM 3D Body

    SAM 3D Body

    Code for running inference with the SAM 3D Body Model 3DB

    SAM 3D Body is a promptable model for single-image full-body 3D human mesh recovery, designed to estimate detailed human pose and shape from just one RGB image. It reconstructs the full body, including feet and hands, using the Momentum Human Rig (MHR), a parametric mesh representation that decouples skeletal structure from surface shape for more accurate and interpretable results.
    Downloads: 10 This Week
    Last Update:
    See Project
  • 9
    Depth Anything 3

    Depth Anything 3

    Recovering the Visual Space from Any Views

    Depth Anything 3 is a research-driven project that brings accurate and dense depth estimation to any input image or video, enabling foundational understanding of 3D structure from 2D visual content. Designed to work across diverse scenes, lighting conditions, and image types, it uses advanced neural networks trained on large, heterogeneous datasets, producing depth maps that reveal scene depth relationships and object surfaces with strong fidelity. The model can be applied to photography, AR/VR content creation, robotics perception, and 3D reconstruction workflows, making it versatile across industries and research domains. ...
    Downloads: 7 This Week
    Last Update:
    See Project
  • Earn up to 16% annual interest with Nexo. Icon
    Earn up to 16% annual interest with Nexo.

    Let your crypto work for you

    Put idle assets to work with competitive interest rates, borrow without selling, and trade with precision. All in one platform. Geographic restrictions, eligibility, and terms apply.
    Get started with Nexo.
  • 10
    TRELLIS 2

    TRELLIS 2

    Native and Compact Structured Latents for 3D Generation

    TRELLIS.2 is a cutting-edge open-source model and codebase for high-fidelity 3D asset generation from 2D images, developed to push forward the state of the art in image-to-3D generation. At its core is a novel sparse voxel structure called O-Voxel that jointly encodes both geometry and surface appearance, enabling reconstruction and generation of complex 3D shapes with arbitrary topology, open surfaces, and physically based rendering (PBR) textures. ...
    Downloads: 40 This Week
    Last Update:
    See Project
  • 11
    ursina

    ursina

    A game engine powered by python and panda3d

    ursina is an easy-to-use, open source game engine and framework for Python that is built on top of Panda3D, aiming to make game development approachable while still being powerful enough for real projects. It lets you create both 2D and 3D games, applications, and visualizations by writing concise Python scripts instead of dealing with a lot of low-level boilerplate. The engine is centered around an Entity-based architecture, where everything in the scene is an object you can easily configure and manipulate from code. Ursina focuses heavily on iteration speed, offering in-game reloading of code, textures, and models so you can tweak and test changes quickly. ...
    Downloads: 41 This Week
    Last Update:
    See Project
  • 12
    Stable Virtual Camera

    Stable Virtual Camera

    Stable Virtual Camera: Generative View Synthesis with Diffusion Models

    Stable Virtual Camera is a multi-view diffusion model developed by Stability AI that transforms 2D images into immersive 3D videos with realistic depth and perspective. Unlike traditional methods that require complex reconstruction or scene-specific optimization, this model allows users to generate novel views from any number of input images and define custom camera trajectories, enabling dynamic exploration of scenes. It supports various aspect ratios and can produce 3D-consistent videos up to 1,000 frames, making it a versatile tool for creators seeking to enhance visual storytelling. ​
    Downloads: 1 This Week
    Last Update:
    See Project
  • 13
    three.js

    three.js

    JavaScript 3D library

    ...A plethora of examples can be found in the project’s website (https://threejs.org/) which use Canvas 2D, SVG and CSS3D renderers that the library also provides.
    Downloads: 71 This Week
    Last Update:
    See Project
  • 14
    glslViewer

    glslViewer

    Console-based GLSL Sandbox for 2D/3D shaders shaders

    GlslViewer is a flexible console-based OpenGL Sandbox to display 2D/3D GLSL shaders without the need of a UI. You can definitely make your own UI or wrapper using the Python Module (include) or any other tool that communicates back/forth with the GPS viewer through the standard POSIX console In/Out or OSC. Default vert/frag shaders for 2D shader and 3D material shaders with PBR lighting model. Hot reload of files on changes.
    Downloads: 14 This Week
    Last Update:
    See Project
  • 15
    Thunder Engine

    Thunder Engine

    Cross-platform 2D and 3D game engine with modular architecture

    Thunder is a lightweight, modular game engine written in C++ that provides a robust foundation for creating 2D and 3D games across platforms. It emphasizes a clean, component-based architecture and is designed for flexibility, performance, and scalability. Thunder includes built-in support for scripting, resource management, physics, animation, and rendering, with tools that facilitate efficient game development and deployment. Its cross-platform nature and minimal dependencies make it suitable for indie developers and small teams looking to build polished games with modern features.
    Downloads: 8 This Week
    Last Update:
    See Project
  • 16
    Open 3D Engine (O3DE)

    Open 3D Engine (O3DE)

    Open 3D Engine (O3DE) is an Apache 2.0-licensed multi-platform 3D

    ...Developed with cutting-edge, real-time graphics and complex interactions in mind, O3DE allows you to create robust, engaging experiences using our multi-threaded and extensible photorealistic renderer. O3DE's modular architecture is built for customization from day one. Each component, known as a Gem, can be adopted separately, giving you access to the specific functionality needed for your application. Add new editing tools, features, and development workflows to your projects. Choose from a variety of community-maintained Gems to extend and enhance the engine's capabilities in anything from AI and robotics to push notifications and VR.With our engine's SDK capabilities, you can use O3DE as a foundation for any type of 3D project you can imagine.
    Downloads: 13 This Week
    Last Update:
    See Project
  • 17
    AliceVision

    AliceVision

    3D Computer Vision Framework

    AliceVision is an open-source photogrammetric computer vision framework designed to reconstruct detailed 3D scenes and camera motion from collections of images or videos. It provides a complete pipeline for structure-from-motion (SfM), multi-view stereo (MVS), and mesh generation, allowing users to convert 2D imagery into accurate 3D models. The framework is built with a strong emphasis on research-grade algorithms while maintaining the robustness required for production environments, making it suitable for industries such as visual effects, cultural heritage preservation, and robotics. ...
    Downloads: 1 This Week
    Last Update:
    See Project
  • 18
    ML Sharp

    ML Sharp

    Sharp Monocular View Synthesis in Less Than a Second

    ML Sharp is a research code release that turns a single 2D photograph into a photorealistic 3D representation that can be rendered from nearby viewpoints. Instead of requiring multi-view input, it predicts the parameters of a 3D Gaussian scene representation directly from one image using a single forward pass through a neural network. The core idea is speed: the 3D representation is produced in under a second on a standard GPU, and then the resulting scene can be rendered in real time to generate new views interactively. ...
    Downloads: 7 This Week
    Last Update:
    See Project
  • 19
    J2ME-Loader

    J2ME-Loader

    A J2ME emulator for Android

    J2ME-Loader is a J2ME emulator for Android. It supports most 2D and 3D games (including Mascot Capsule 3D ones). Emulator has a virtual keyboard, individual settings for each application, scaling support. This project is a fork of J2meLoader. Enabling filtering in some cases can greatly reduce performance. Disable this option if the game is too slow. Image flickering issues can be fixed by enabling the "Immediate processing mode" option.
    Downloads: 18 This Week
    Last Update:
    See Project
  • 20
    rayshader

    rayshader

    R Package for 2D and 3D mapping and data visualization

    This is an R package designed for producing beautiful and interactive 2D and 3D visualizations — especially maps and terrain renderings — using elevation/gridded data and ray-tracing / hill-shading methods. At its core, rayshader takes a matrix of elevations and applies shading, texture, ambient occlusion, overlays, and light modeling (ray shade, lambertian shading, etc.) to produce realistic relief maps.
    Downloads: 0 This Week
    Last Update:
    See Project
  • 21
    Cocos Engine

    Cocos Engine

    Cocos simplifies game creation and distribution with Cocos Creator

    ...Because of its cross-platform nature, games built with cocos-engine (via Cocos Creator) can target mobile, desktop, and web, making it a popular choice for developers wanting flexibility and broad reach. The engine includes extensive tooling and example/demo projects to demonstrate 2D and 3D physics, animation, UI and rendering capabilities.
    Downloads: 16 This Week
    Last Update:
    See Project
  • 22
    Microsoft Paint 3D

    Microsoft Paint 3D

    Free app for creating 3D art

    Microsoft Paint 3D is a free creative application bundled with Windows 10 and later versions that lets users easily create and edit 3D and 2D artwork. It updates the classic Microsoft Paint with powerful yet user-friendly 3D modeling tools that require no prior design experience. Users can customize existing 3D models or build new ones from scratch using a variety of shapes, brushes, and effects.
    Downloads: 111 This Week
    Last Update:
    See Project
  • 23
    LayaAir3.0

    LayaAir3.0

    LayaAir is an open-source 2D/3D engine

    The LayaAir engine is a game engine brand under Layabox . The LayaAir engine not only supports 2D, 3D, AR, VR and other types of game development but also can be used in advertising, marketing, education and other fields. In addition to the release of the HTML5 version, it also supports the release of Native-APP, WeChat mini-games, QQ mini-games, Baidu mini-games, Bilibili mini-games, Douyin mini-games, Toutiao mini-games, Alipay mini-games, OPPO mini-games, and vivo mini-games. ...
    Downloads: 2 This Week
    Last Update:
    See Project
  • 24
    Juggling Lab

    Juggling Lab

    Juggling Lab juggling animator

    Juggling Lab is an open-source juggling simulation and animation software designed to visualize juggling patterns. It allows users to create, simulate, and analyze various juggling sequences, offering both 2D and 3D visualizations. Juggling Lab is highly customizable, supporting complex patterns and siteswap notation, making it a valuable tool for jugglers, performers, and enthusiasts looking to practice or study new routines.
    Downloads: 20 This Week
    Last Update:
    See Project
  • 25
    Axmol Engine

    Axmol Engine

    Multi-platform Engine for Desktop, XBOX (UWP) and Mobile games

    Axmol is a modern C++ game engine forked from Cocos2d-x, designed to support high-performance 2D and lightweight 3D game development across multiple platforms. It improves upon the original Cocos2d-x with a cleaner architecture, better tooling, and support for modern C++ standards. Axmol supports scripting with Lua and JavaScript, and is suitable for both indie developers and studios targeting mobile, desktop, and web platforms.
    Downloads: 9 This Week
    Last Update:
    See Project
  • Previous
  • You're on page 1
  • 2
  • 3
  • 4
  • 5
  • Next
MongoDB Logo MongoDB