Awesome GitHub RepositoriesBackground Removal Tools

Facefusion is a modular framework designed for automated image and video manipulation, specializing in tasks such as face swapping, enhancement, and restoration. It functions as a computer vision processing pipeline that chains independent machine learning modules to perform complex transformations, including facial animation, age modification, and lip synchronization. The system is built to handle both real-time interactive feeds and large-scale batch processing tasks. The platform distinguishes itself through a highly extensible architecture that supports custom processing modules and inter

IOPaint is an AI image editor and Stable Diffusion inpainting tool providing a web interface for removing objects and replacing image content. It utilizes latent diffusion image processing to synthesize high-resolution replacements for erased sections of an image. The project features a specialized AI background remover for isolating subjects and an AI image upscaler that employs super-resolution models for general photos and anime artwork. The software covers a broad range of capabilities including image segmentation for object isolation, face restoration for improving facial details, and t

Lama Cleaner is an AI-powered image editing application focused on inpainting, object removal, and generative filling. It provides a suite of tools for erasing unwanted elements from photos and filling the resulting gaps using generative artificial intelligence. The project includes specialized capabilities for image outpainting to extend borders, background removal through object segmentation, and face restoration to fix visual defects. It also features an image upscaler to increase resolution and clarity via super-resolution AI, as well as a Stable Diffusion-based editor for replacing speci

Rembg is a machine learning-based toolkit designed for automated image background removal and subject segmentation. It functions as a versatile engine that identifies and extracts subjects from images, supporting diverse input methods including individual files, directory-based batch processing, and live binary data streams. The project distinguishes itself through its flexible integration options, offering a command-line interface for local automation, a library for programmatic access, and an HTTP service for remote requests. It utilizes deep learning architectures to classify pixels and ge

HivisionIDPhotos is an AI-powered identification photo generator designed to automate the creation of standardized portraits. It utilizes machine learning to handle alignment, cropping, and background removal, transforming regular images into official identification photographs. The system features a background removal tool that uses offline inference to isolate subjects and a portrait enhancement tool that applies beauty filters to improve facial appearance and skin quality. To prepare photos for physical use, it includes a print layout generator that arranges processed images into standard

Perfect Green Screen Keys

This project is a comprehensive software entrepreneurship curriculum and solopreneurship business playbook designed for developers. It provides a strategic framework for building, validating, and monetizing side businesses using lean startup methodology and a systematic product development approach. The project distinguishes itself by offering specific guides for digital monetization and career anti-fragility, helping software engineers transition from employment to self-employment. It focuses on turning technical skills into scalable digital assets, paid communities, and independent software

Paper2gui is a multi-modal AI toolkit and model GUI wrapper designed to deploy and run various artificial intelligence models through a visual interface. Its primary purpose is to provide a way to execute complex AI research papers and models without requiring manual software installation or coding. The project distinguishes itself by using a wrapper-based model interface that abstracts command line arguments into visual input fields, utilizing template-driven UI generation to create parameter sliders and forms based on the specific requirements of the underlying model. It includes a centrali

U-2-Net is a PyTorch image segmentation framework and computer vision saliency model designed to generate high-resolution foreground-background masks. It functions as an AI background removal tool that identifies and isolates the most visually prominent objects within an image. The model utilizes a nested U-structure design to detect salient objects, creating precise cutouts by predicting saliency maps. These capabilities enable the separation of main subjects from their surroundings to create transparent images. The framework covers several image processing workflows, including automatic ba

RobustVideoMatting is a deep learning video matting tool and PyTorch library designed to remove backgrounds from videos and extract human subjects. It utilizes a temporal video segmentation model to ensure consistent matting and reduce flickering across video frames. The project includes a cross-platform model exporter that converts trained neural networks into various runtime formats. This allows for model deployment across multiple environments, including web and mobile applications. The framework provides capabilities for temporal video background removal and AI video post-production with

This project is a diffusion-based 3D generator and image-to-3D reconstruction system. It translates natural language descriptions or two-dimensional images into three-dimensional assets using neural radiance fields and diffusion models. The system utilizes score-distillation sampling and diffusion-based guidance to refine 3D shapes without requiring 3D training data. It includes specialized tools for transforming neural representations into exportable meshes with texture and material data, as well as a pipeline for iterative optimization of geometry and textures. The project covers a broad r

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

Backgroundremover is an AI-powered tool that removes backgrounds from both images and videos, accessible through a command-line interface and a Python API. At its core, it uses a pre-trained deep learning model to classify each pixel as foreground or background, producing a binary mask for removal. The tool distinguishes itself through multiple integration methods and output capabilities. It can process images and videos via Unix pipeline data streams, operate as an HTTP API server, or be called programmatically within Python scripts. Users can choose among different AI models to balance proc

OpenDroneMap (ODM) is an open-source aerial drone photogrammetry pipeline that converts 2D images into georeferenced 3D models, orthophotos, point clouds, and digital elevation maps. At its core, the OpenDroneMap Processing Engine orchestrates a complete Structure-from-Motion workflow, from feature extraction through dense reconstruction and tiled output generation, purpose-built for transforming drone-captured imagery into geospatial data products. The toolkit distinguishes itself through GPU-accelerated SIFT feature extraction using CUDA-capable NVIDIA graphics cards, roughly doubling proce

Natron es un software de composición de video y gráficos en movimiento basado en nodos de código abierto. Funciona como una herramienta de efectos visuales que combina imágenes y video utilizando un grafo de nodos y una canalización de color lineal para crear efectos complejos y extensiones de set. El software incluye una suite de seguimiento de movimiento 2D para estabilizar metraje y rastrear el movimiento de píxeles a través de fotogramas. Es un entorno programable en Python, lo que permite una automatización personalizada y extensiones de interfaz de usuario a través de un intérprete de Python integrado. La plataforma proporciona una gama completa de capacidades de composición, incluyendo chroma keying, rotoscopia y procesamiento de imágenes multicanal. Soporta animación basada en fotogramas clave con editores de curvas y ofrece un motor de renderizado headless para procesamiento por lotes a través de una interfaz de línea de comandos. El rendimiento se gestiona a través de un motor de renderizado multihilo y un sistema de vista previa basado en proxy para mantener la retroalimentación en tiempo real. El sistema también utiliza una arquitectura de plugins estandarizada para integrar herramientas de procesamiento visual de terceros.

obs-multi-rtmp es un plugin para OBS Studio que permite transmitir un mismo feed de video a múltiples destinos RTMP simultáneamente. Funciona como una extensión del software de transmisión para añadir gestión de destinos de salida para transmisiones en vivo. La herramienta duplica un stream de video en vivo y lo envía a varias plataformas de streaming a la vez. Esto permite la transmisión RTMP simultánea a endpoints redundantes o distribuidos sin duplicar los codificadores. El proyecto gestiona la transmisión en vivo multiplataforma mediante streaming RTMP multiplexado y replicación de datos basada en sockets. Emplea E/S de red asíncrona y gestión de buffers específica por destino para manejar múltiples streams salientes en paralelo.

lite.ai.toolkit es un toolkit de visión artificial en C++ diseñado para el despliegue de IA en el borde (edge). Permite la ejecución de modelos preentrenados para detección de objetos, clasificación de imágenes y segmentación en dispositivos con recursos limitados. El proyecto cuenta con un motor de inferencia multi-backend que admite el runtime de modelos ONNX, permitiendo que los modelos de IA se ejecuten en diferentes objetivos de hardware. Incluye un pipeline acelerado por GPU específicamente para hardware NVIDIA para reducir la latencia y aumentar la velocidad de procesamiento. El toolkit cubre una amplia gama de capacidades de análisis facial, incluyendo detección de emociones, estimación de género y edad, y análisis de pose de cabeza. También proporciona herramientas para el reconocimiento facial mediante la extracción de embeddings de características y el cálculo de similitud de coseno para verificar identidades. Las capacidades adicionales incluyen el matting de imágenes para el aislamiento del primer plano, la colorización de imágenes en escala de grises y la transferencia de estilo artístico.

obs-websocket es un plugin y extensión de control remoto WebSocket para OBS Studio. Funciona como una API de red JSON-RPC que permite a dispositivos y aplicaciones externas gestionar ajustes de software, escenas y operaciones de streaming. El proyecto proporciona un protocolo de red estandarizado que permite la ejecución de comandos remotos y la sincronización de estado basada en eventos. Asegura estas conexiones utilizando autenticación de desafío con sal (salted-challenge) para verificar la identidad del cliente. La interfaz cubre una amplia gama de capacidades de producción, incluyendo gestión de escenas y fuentes, control de niveles de audio y gestión de salida para grabación y streaming. También admite consultas de estadísticas del sistema y monitoreo del estado del software para facilitar el monitoreo de transmisiones en tiempo real y la automatización del flujo de trabajo.

StreamFX-Public es una colección de plugins de OBS Studio y componentes de software diseñados para la mejora de transmisiones. Proporciona un conjunto de efectos visuales, filtros, codificadores acelerados por hardware y herramientas de codificación de video profesional para ampliar las capacidades de la aplicación anfitriona. El proyecto se distingue por el soporte de códecs de video mezzanine profesionales, incluyendo DNxHR, ProRes y Cineform, para edición de postproducción de alta fidelidad. También implementa grabación acelerada por hardware a través de núcleos de GPU y AMD AMF para reducir la sobrecarga de CPU durante las transmisiones en vivo. El conjunto de herramientas cubre efectos visuales en tiempo real utilizando renderizado basado en shaders para transformaciones 3D, desenfoque de regiones y enmascaramiento. Además, incluye herramientas de transición de escenas personalizadas que utilizan shaders para controlar el reemplazo visual de fuentes durante los cambios de transmisión.

This project is a plugin for OBS Studio that uses neural networks to isolate subjects from backgrounds in real-time video streams. It functions as an AI video segmentation tool that predicts portrait masks to create virtual green-screen effects without the need for physical hardware. The software includes a real-time depth estimation filter that identifies scene depth to produce a blurred background while keeping the foreground subject in focus. It also provides low-light video enhancement to improve visibility and visual quality for portrait video captured in poorly lit environments. The pl