Projects sharing features with Gaussian Splatting

Meshroom is a node-based photogrammetry software designed to transform collections of two-dimensional images into three-dimensional models and scene geometry. It provides a visual interface for constructing and managing modular data pipelines, allowing users to automate complex computer vision tasks such as feature extraction, depth map estimation, and mesh generation. The software distinguishes itself through a distributed computational framework that dispatches resource-intensive tasks across local hardware or remote render farms. By utilizing a directed acyclic graph execution model, it en

PyTorch3D is a 3D geometric deep learning library and mesh processing toolkit designed for learning from point clouds and complex 3D surface geometries. It provides a collection of reusable components and data structures for deep learning with 3D data, including a framework for training and evaluating neural radiance fields to enable photorealistic view synthesis. The project features a differentiable 3D renderer that converts meshes and point clouds into 2D images while allowing gradients to flow back into the geometry and textures. This enables 3D shape optimization, where mesh geometry, te

This project is a computer vision pipeline and volumetric rendering system used to transform photos and videos into high-fidelity 3D models. It implements a deformable neural radiance field framework that optimizes deformation fields to represent non-rigid moving subjects in three dimensions. The system utilizes volumetric deformation fields to map 3D coordinates from a static canonical space to a deformed state. This allows for the reconstruction of photorealistic scenes and the synthesis of high-fidelity images from camera perspectives not present in the original input data. The framework

Depth-Anything-3 is a collection of core model implementations for depth prediction, multi-view geometry estimation, and RGB-D spatial pipelines. It includes a monocular depth estimation model for predicting depth maps from single images or video, and a 3D Gaussian splatting generator that predicts parameters to synthesize high-fidelity novel views of a scene. The project provides a multi-view geometry estimator for calculating spatially consistent depth and camera poses across synchronized visual inputs. It also functions as a visual SLAM enhancement tool designed to reduce drift and improve

Genesis is an embodied AI simulation platform and parallelized robotics simulator designed for training general-purpose robotic agents. It integrates a physics engine for robotics that calculates collisions and movements for rigid bodies, soft tissues, and fluids, alongside a photorealistic 3D rendering engine. The platform features a domain randomization framework to vary environment parameters across parallel simulations, aiding in sim-to-real transfer. It supports the integration of real-world captured light fields and Gaussian splatting to provide photorealistic backgrounds within simulat

This project is a static educational website and comprehensive curriculum focused on computer vision and deep learning. It serves as a public repository of instructional materials, lecture notes, and technical guides specifically detailing convolutional neural networks and visual recognition. The site is developed using static-site generation to host course documentation and student project directories. It provides structured academic resources that guide learners through image classification, generative modeling, and the implementation of various neural network architectures. The curriculum

A free and open source implementation of 3D gaussian splatting written in C++, focused on being portable, lean and fast.

This project is a high-performance C++ and CUDA neural network library designed for fast training and inference of small networks on NVIDIA GPUs. It serves as a specialized backend for neural radiance fields and coordinate-based networks, providing a fused GPU kernel library and a hash grid encoder for transforming raw input dimensions into high-dimensional representations. The library distinguishes itself through the use of C++ template metaprogramming and fused-kernel execution, which merge neural network layers into single GPU device functions to eliminate memory bottlenecks. It leverages

This project is an educational codebase and reference library that translates theoretical deep learning concepts into executable PyTorch code. It serves as a practical implementation of a deep learning textbook, providing a course-like structure of guided exercises and architectural examples for learning purposes. The repository includes a library of standard neural network architectures, including linear, convolutional, recurrent, and transformer models. It specifically implements a variety of deep learning patterns such as multilayer perceptrons, VGG networks, gated recurrent units, and lon

This project is a collection of interactive notebooks for a TensorFlow deep learning course. It provides guided learning resources and practical tutorials for implementing neural network architectures, supervised learning, and transfer learning. The materials feature a computer vision learning path and specific guides for transfer learning, demonstrating how to adapt pre-trained models to new tasks. It includes tutorials for building regression models and image classifiers using the Keras high-level API. The scope covers supervised learning pipelines for binary and multiclass classification,

Ogre is a high-level 3D rendering engine designed for creating games, simulations, and visualizations without requiring low-level graphics API code. It functions as a framework for real-time 3D graphics processing, providing a physically based renderer to simulate lifelike surfaces and lighting. The engine includes specialized systems for skeletal animation to control character movement and a terrain generation system for producing large textured landscapes. These features are supported by automatic levels of detail and distance-based mesh management to maintain performance. The project cove

This project is a high-level 3D graphics engine designed to render complex, hardware-accelerated environments within web browsers. It provides a comprehensive abstraction layer that manages scene graphs, cameras, and lighting, mapping high-level scene definitions onto low-level graphics APIs. By decoupling these definitions from specific hardware targets, the engine ensures consistent performance across diverse browsers and devices. The framework distinguishes itself through a robust architecture that includes a unified math library for high-frequency spatial calculations and a physically bas

MultiNeRF is a 3D scene reconstruction suite and framework for training Neural Radiance Fields to synthesize novel views from sets of 2D images. It provides a system for generating new perspectives of a scene by optimizing a neural network based on images and camera poses. The toolkit includes research implementations such as Mip-NeRF 360 and Ref-NeRF for high-fidelity volumetric rendering. It features a structure-from-motion pipeline to calculate camera positions and orientations from image datasets to prepare data for training. The project covers a full workflow for volumetric rendering, i

Hazel is a C++ game development framework and 3D graphics rendering engine designed for building high-performance interactive software. It provides a foundational architecture that enables the construction of desktop applications through native hardware acceleration. The project includes a dedicated game engine editor that allows for the design and testing of interactive 3D and 2D scenes within a unified environment. This editor utilizes an immediate mode interface to maintain synchronization with the engine state, while a hardware-agnostic abstraction layer handles rendering commands across

VGGT is a computer vision framework designed for neural scene reconstruction and 3D environmental modeling. It utilizes a feed-forward neural architecture to process input images, simultaneously inferring camera parameters, depth maps, and point trajectories to generate dense 3D point clouds. The system distinguishes itself by integrating multi-view geometry with temporal tracking, allowing it to maintain spatial consistency across sequential frames. By leveraging pretrained neural backbones, the framework extracts robust visual features that support complex geometric tasks, including the ana

openMVS is a multi-view stereo library and photogrammetry pipeline used for 3D scene reconstruction. It transforms Structure from Motion data—specifically camera poses and sparse point clouds—into detailed 3D models consisting of dense point clouds and textured meshes. The project provides a sequence of processing stages to densify point clouds, generate 3D surface meshes, and apply photorealistic textures. It uses multi-view texture blending to map accurate colors onto reconstructed geometry and employs iterative refinement to optimize mesh details. The system includes capabilities for impo

NonEuclidean is a graphics framework and rendering engine designed to compute and display three-dimensional scenes using non-standard spatial rules and geometries. It serves as a visualization tool for exploring complex mathematical spaces where traditional Euclidean laws of distance and angle do not apply. The project implements custom rendering pipelines to visualize non-standard geometric projections and warped spatial logic. This includes the ability to map non-Euclidean coordinates to Poincaré disk or Klein models to render curved space on flat screens. The system utilizes dynamic metri

This project is a framework for neural radiance fields used to synthesize three-dimensional environments from sets of two-dimensional images and camera poses. It functions as a volumetric rendering engine and scene synthesizer that optimizes neural representations of spatial volumes to generate novel views of complex 3D scenes. The system implements a coordinate encoding system that transforms spatial coordinates into high-dimensional space to capture high-frequency geometric details. It also includes a neural mesh extractor that converts trained radiance fields into triangle meshes via march

FlaxEngine is a cross-platform game engine and development kit designed for creating high-fidelity 2D and 3D games. It functions as a programmable framework that supports the use of C# and C++ for building interactive experiences. The project includes a high-speed graphics rendering engine capable of producing professional visual assets and detailed three-dimensional scenes. It provides a pipeline for compiling and exporting project files across various operating systems using native software development kits and toolchains.

This project is a 3D animation suite and legacy software archive consisting of original source code and build scripts. It functions as a historical rendering engine and computer graphics reference for analyzing the asset management and rendering frameworks used in mid-nineties multimedia production. The codebase allows for the restoration of legacy software by compiling original source code into executable binaries for modern hardware. It serves as a resource for software archaeology research and the study of vintage multimedia development. The system enables the production of three-dimensio

Babylon.js is a JavaScript game engine and real-time graphics renderer designed for creating interactive three-dimensional visuals and applications. It functions as a web-based 3D framework and WebGL engine that enables the deployment of high-performance 3D content across various web platforms and devices. The project provides tools for web-based 3D game development, real-time graphics rendering, and the creation of browser-based interactive visualizations. It also supports the development of WebXR virtual and augmented reality experiences using standard web technologies. The framework cover

Gameplay is a high-performance C++ game engine and cross-platform framework designed for developing 2D and 3D interactive games. It functions as both a 3D graphics engine for rendering environments and a 2D game development kit for creating sprite-based mechanics. The framework provides a cross-platform abstraction layer to ensure that game logic and graphics run across various hardware and software platforms using a shared codebase. The engine implements a hardware-accelerated rendering pipeline and component-based game logic to separate data from behavior. It utilizes a native C++ impleme

ml-sharp is a neural radiance field framework designed for single-image 3D reconstruction. It uses a neural network to predict 3D geometry and appearance from a single photograph in a single feedforward pass. The system generates metric 3D scene representations and includes a real-time view synthesizer for producing high-resolution images of new viewpoints. It also features a camera trajectory renderer that creates video sequences by moving a virtual camera through the predicted 3D space. The project covers coordinate-based neural rendering, 3D Gaussian representation regression, and real-ti

Panda3D is a cross-platform game engine and 3D graphics rendering system developed for Python and C++. It functions as a comprehensive framework for building interactive 3D applications, providing a real-time physics simulator and a specialized 3D asset pipeline tool. The engine distinguishes itself by combining a high-performance C++ core with interoperable Python language bindings. It utilizes a scene graph architecture to organize 3D objects and provides a pipeline-based asset conversion system to optimize models and textures for runtime loading. Its capability surface includes low-level

Stride is a C# game engine and 3D rendering engine used for building three-dimensional games and virtual reality applications. It functions as a comprehensive framework and development kit for creating immersive experiences within a managed code environment. The project includes a developer GUI framework for building internal debugging tools and utility panels. It also serves as a 3D physics simulator for calculating rigid body dynamics and collision detection within a scene. The engine covers environmental scene rendering and project scaffolding workflows. It provides tooling for game devel

WickedEngine is a C++ 3D game engine and framework designed for building high-fidelity three-dimensional applications and graphics projects. It features a modern graphics renderer that implements current standards to produce complex geometry and lighting across different hardware. The engine includes a standalone visual scene editor for designing environments and configuring properties without writing code. It also provides an integrated Lua scripting environment to manage runtime logic and automate engine tasks. The framework covers 3D graphics rendering and application development, includi