awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descubre los mejores repositorios open-source con nuestra búsqueda potenciada por IA.

ExplorarBúsquedas curadasAlternativas open-sourceSoftware autohospedableBlogMapa del sitio
ProyectoServidor MCPAcerca deCómo clasificamosPrensa
Aviso legalPrivacidadTérminos
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

13 repositorios

Awesome GitHub RepositoriesImage Background Removal

Tools and algorithms for isolating a foreground subject from its background to create transparency.

Distinct from Image Removal: None of the candidates provide a general image-based background removal tag that is not video-centric or PDF-centric

Explore 13 awesome GitHub repositories matching graphics & multimedia · Image Background Removal. Refine with filters or upvote what's useful.

Awesome Image Background Removal GitHub Repositories

Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
  • cyrildiagne/ar-cutpasteAvatar de cyrildiagne

    cyrildiagne/ar-cutpaste

    14,577Ver en GitHub↗

    ar-cutpaste is an augmented reality asset extraction tool and prototype designed to isolate objects from a live camera feed and transfer them into image editing software. It functions as a mobile-to-desktop bridge that uses machine learning to remove backgrounds from live images, creating digital cutouts for use in image composition. The system establishes a local server connection to transmit image data and spatial coordinates from a mobile device to a design application. This bridge uses a remote socket mechanism and a secure password to inject captured assets directly into a desktop worksp

    Uses machine learning to isolate specific objects from a live camera feed by removing the surrounding background.

    TypeScript
    Ver en GitHub↗14,577
  • xuebinqin/u-2-netAvatar de xuebinqin

    xuebinqin/U-2-Net

    9,773Ver en GitHub↗

    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

    Separates the main object from its surroundings to create transparent cutouts.

    Pythoncomputer-visiondeep-learningimage-background-removal
    Ver en GitHub↗9,773
  • nadermx/backgroundremoverAvatar de nadermx

    nadermx/backgroundremover

    7,932Ver en GitHub↗

    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

    Removes backgrounds from single image files using AI segmentation, supporting JPG, PNG, and HEIC formats.

    Pythonaibackground-removalbackground-remover
    Ver en GitHub↗7,932
  • imgly/background-removal-jsAvatar de imgly

    imgly/background-removal-js

    7,192Ver en GitHub↗

    Background Removal JS is a client-side neural matting library that runs a lightweight AI model directly in the browser to compute alpha mattes, removing image backgrounds without uploading any data to a server. It functions as a browser-based image background removal SDK and client-side image matting library, keeping all processing on the user's device to eliminate server costs and preserve privacy. The project provides a cross-platform creative editing engine that produces identical image and video output across web, mobile, desktop, and server environments from a single codebase. It offers

    Removes image backgrounds entirely in the browser using on-device AI, eliminating server costs and preserving privacy.

    TypeScriptbackground-removalimage-mattingimage-segmentation
    Ver en GitHub↗7,192
  • peterl1n/backgroundmattingv2Avatar de PeterL1n

    PeterL1n/BackgroundMattingV2

    7,178Ver en GitHub↗

    BackgroundMattingV2 is a deep learning background matting tool and real-time image segmentation framework. It provides a system for isolating foreground subjects from high-resolution images and video feeds in real time. The project includes a deep learning model trainer for optimizing matting models through base convergence and end-to-end refinement. It also functions as a cross-runtime model exporter, converting trained neural networks into interchangeable formats for deployment across different software environments and hardware runtimes. The framework supports streaming processed webcam f

    Isolates foreground subjects from high-resolution images and videos to remove the background.

    Pythoncomputer-visionmachine-learningmatting
    Ver en GitHub↗7,178
  • opendronemap/opendronemapAvatar de OpenDroneMap

    OpenDroneMap/OpenDroneMap

    6,196Ver en GitHub↗

    A command line toolkit to generate maps, point clouds, 3D models and DEMs from drone, balloon or kite images. 📷

    Filters out sky or other non-relevant areas from input photos before processing to improve reconstruction quality.

    Python
    Ver en GitHub↗6,196
  • chainner-org/chainnerAvatar de chaiNNer-org

    chaiNNer-org/chaiNNer

    5,855Ver en GitHub↗

    chaiNNer is a GPU-accelerated AI image upscaling application that uses a visual node-based interface for constructing image processing pipelines. At its core, it provides a node-based visual programming environment where users connect processing nodes in a directed acyclic graph, with a graph execution scheduler that traverses the pipeline in topological order. The application includes an iterator-based batch processing system that automatically applies the same pipeline to multiple files, and a model format conversion pipeline that transforms neural network models between PyTorch, ONNX, and N

    Separates foreground subjects from backgrounds using pre-trained neural network models in a visual pipeline.

    Python
    Ver en GitHub↗5,855
  • lxfater/inpaint-webAvatar de lxfater

    lxfater/inpaint-web

    5,834Ver en GitHub↗

    A free and open-source inpainting & image-upscaling tool powered by webgpu and wasm on the browser。| 基于 Webgpu 技术和 wasm 技术的免费开源 inpainting & image-upscaling 工具, 纯浏览器端实现。

    Performs all image editing operations locally in the browser without sending data to any server.

    TypeScriptimage-upscalinginpaintingsuper-resolution
    Ver en GitHub↗5,834
  • senguptaumd/background-mattingAvatar de senguptaumd

    senguptaumd/Background-Matting

    4,772Ver en GitHub↗

    Este proyecto es un framework de matting de imágenes de aprendizaje profundo y una herramienta de visión artificial diseñada para separar a las personas de sus fondos. Funciona como un motor de matting de video en tiempo real y un modelo de aislamiento de primer plano entrenable que genera mattes alfa por píxel para aislar sujetos de fotos y videos. El sistema utiliza matting alfa basado en referencia, incorporando una imagen de fondo específica para simular efectos de pantalla verde sin una pantalla física. Este enfoque permite la eliminación y sustitución de fondos en metraje de alta resolución, incluyendo transmisiones de video en vivo. El framework admite matting de alta resolución y procesamiento de video en tiempo real. También proporciona capacidades para el entrenamiento de modelos de matting personalizados, permitiendo a los usuarios entrenar redes neuronales en conjuntos de datos específicos con resoluciones y arquitecturas configurables.

    Extracts people from photos by generating a per-pixel alpha matte for transparency.

    Python
    Ver en GitHub↗4,772
  • palxiao/poster-designAvatar de palxiao

    palxiao/poster-design

    4,731Ver en GitHub↗

    Este proyecto es un editor de diseño gráfico basado en web y diseñador de pósteres en línea. Proporciona un entorno basado en navegador para crear diseños visuales profesionales, gráficos de comercio electrónico y portadas para redes sociales utilizando un lienzo con elementos de arrastrar y soltar. El kit de herramientas incluye un convertidor de plantillas PSD especializado que analiza archivos de diseño de Photoshop para convertirlos en plantillas web editables. También cuenta con un generador de códigos QR personalizado capaz de producir códigos estilizados con degradados y logotipos incrustados, junto con una herramienta de manipulación de imágenes basada en navegador para recortar activos y eliminar fondos. El editor cubre capacidades amplias de diseño gráfico, incluyendo la gestión de mesas de trabajo y capas, formato de tipografía con efectos CSS y asistencia de alineación espacial mediante guías y reglas. La salida de alta fidelidad se logra a través de un proceso híbrido de renderizado en el frontend y el servidor para asegurar una reproducción precisa de la imagen. El sistema soporta la gestión de plantillas de usuario para almacenar y actualizar diseños personalizados.

    Features a background removal tool with cutout capabilities and manual brush repairs for image isolation.

    Vuecanvasdesignimage
    Ver en GitHub↗4,731
  • zhkkke/modnetAvatar de ZHKKKe

    ZHKKKe/MODNet

    4,331Ver en GitHub↗

    MODNet is a deep learning image segmenter and portrait matting model designed to isolate human subjects from backgrounds. It generates high-quality alpha mattes for images and video using only standard RGB input, removing the requirement for manual trimap guides. The framework is optimized for real-time inference and provides utilities to export pre-trained model weights into specialized formats for deployment on target hardware. The project covers the full workflow for portrait isolation, including supervised matting model training on labeled datasets, real-time video background removal, an

    Generates alpha mattes to isolate foreground subjects from backgrounds using only standard RGB input.

    Pythonportrait-matting
    Ver en GitHub↗4,331
  • minivision-ai/photo2cartoonAvatar de minivision-ai

    minivision-ai/photo2cartoon

    4,027Ver en GitHub↗

    photo2cartoon es una herramienta de software basada en visión y framework de entrenamiento diseñado para convertir fotografías de retratos humanos reales en imágenes de dibujos animados estilizadas. Utiliza redes generativas antagónicas (GAN) para traducir imágenes de un dominio del mundo real a un estilo de dibujos animados. El proyecto incluye un framework de entrenamiento para estos modelos que soporta supervisión de datos emparejados y entrenamiento distribuido en múltiples GPU. Emplea funciones de pérdida que preservan la identidad para asegurar que las salidas de dibujos animados resultantes retengan los rasgos faciales originales del sujeto. El sistema incorpora un pipeline de preprocesamiento completo que maneja la detección de rostros, alineación de puntos clave y eliminación de fondo para preparar retratos para la transferencia de estilo.

    Provides a pipeline to isolate the primary subject from the image background to improve cartoonization quality.

    Pythonavatar-generatorcartooncomputer-vision
    Ver en GitHub↗4,027
  • plemeri/transparent-backgroundAvatar de plemeri

    plemeri/transparent-background

    1,255Ver en GitHub↗

    Este software es una utilidad de visión artificial diseñada para el aislamiento automatizado de sujetos y la eliminación de fondos. Proporciona una interfaz de escritorio gráfica que permite a los usuarios extraer sujetos en primer plano de imágenes estáticas, archivos de video y streams de webcam en vivo sin requerir interacción de línea de comandos. La aplicación aprovecha modelos de deep learning para generar máscaras alfa de alta fidelidad, permitiendo la creación de fondos transparentes o la aplicación de reemplazos personalizados. Utilizando procesamiento de tensores acelerado por hardware, el sistema realiza segmentación en tiempo real en feeds de cámara en vivo y procesamiento frame-a-frame para archivos de video, asegurando una salida consistente a través de datos temporales. La herramienta incluye gestión de configuración modular, permitiendo a los usuarios ajustar checkpoints de modelos y ajustes de entorno para adaptarse a requisitos específicos de hardware o almacenamiento. Se distribuye como una aplicación de escritorio, proporcionando un entorno visual para tareas de procesamiento de medios.

    Extracts the foreground subject from an image and replaces the background with transparency, solid colors, blur effects, or custom background images.

    Pythonbackground-removaldeep-learningdichotomous-image-segmentation
    Ver en GitHub↗1,255
  1. Home
  2. Graphics & Multimedia
  3. Image Background Removal

Explorar subetiquetas

  • Browser-Based SDKsAn SDK that removes image backgrounds entirely in the browser using on-device AI, with no server costs or privacy concerns. **Distinct from Image Background Removal:** Distinct from Image Background Removal: specifies an SDK form factor for browser-based background removal.
  • Client-Side ProcessingRemoving backgrounds from images entirely in the browser using on-device AI, eliminating server costs and preserving user privacy. **Distinct from Image Background Removal:** Distinct from Image Background Removal: specifies client-side execution for privacy and cost benefits, not general background removal.
  • Editor IntegrationsAdd a one-click background removal action to a design canvas so users can edit images without leaving the editor. **Distinct from Image Background Removal:** Distinct from Image Background Removal: specifies integration into a design editor canvas, not standalone background removal.
  • Preview IntegrationsDisplays processed images on screen so users can inspect background removal quality before saving. **Distinct from Image Background Removal:** Distinct from Image Background Removal: focuses on the preview step before saving, not the removal itself.
  • Server-Side Execution1 sub-etiquetaPerform the same image matting process on the server side instead of the browser when needed. **Distinct from Image Background Removal:** Distinct from Image Background Removal: specifies server-side execution as an alternative to client-side processing.