Open-source alternatives to Background Matting

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

This software is a computer vision utility designed for automated subject isolation and background removal. It provides a graphical desktop interface that allows users to extract foreground subjects from static images, video files, and live webcam streams without requiring command-line interaction. The application leverages deep learning models to generate high-fidelity alpha masks, enabling the creation of transparent backgrounds or the application of custom replacements. By utilizing hardware-accelerated tensor processing, the system performs real-time segmentation on live camera feeds and

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

mmagic is a multimodal training pipeline and framework for generative AI, focusing on visual synthesis and restoration. It provides the infrastructure to build and train models for tasks such as text-to-image and text-to-video generation, 3D-aware content synthesis, and high-fidelity image translation using diffusion models and generative adversarial networks. The project distinguishes itself through specialized capabilities for generative model personalization, including techniques for fine-tuning subjects and styles. It also supports advanced visual manipulations such as latent space interp

Perfect Green Screen Keys

This project is a system-level utility for Linux that intercepts, modifies, and presents live webcam feeds as standard virtual video devices. By creating a bridge between physical hardware and user-space applications, it allows video conferencing software to consume processed streams as if they were native camera inputs. The software distinguishes itself through its ability to manage the lifecycle of video processing tasks as persistent background services. It monitors virtual device activity to dynamically allocate resources, ensuring that image processing and hardware usage are suspended wh

Darkflow is an object detection framework and computer vision pipeline that provides a programmatic interface for performing real-time image analysis and object identification. It functions as a tool for loading weights, fine-tuning models, and executing inference on both static images and video feeds. The project serves as a converter that translates Darknet configurations and weights into TensorFlow graphs to enable retraining and deployment. It includes a model exporter that saves trained graphs into portable protobuf files for use on mobile and native devices. The system covers capabilit

lite.ai.toolkit is a C++ computer vision toolkit designed for edge AI deployment. It enables the execution of pre-trained models for object detection, image classification, and segmentation on resource-constrained devices. The project features a multi-backend inference engine that supports the ONNX model runtime, allowing AI models to run across different hardware targets. It includes a GPU-accelerated pipeline specifically for NVIDIA hardware to reduce latency and increase processing speed. The toolkit covers a broad range of facial analysis capabilities, including emotion detection, gender

Lama is an image restoration framework and deep learning model designed for image inpainting and object removal. It provides the tools necessary to train and evaluate neural networks that fill masked areas and repair corrupted visual data. The system utilizes a Fourier convolution neural network to maintain global image structure and reconstruct periodic patterns. This architecture allows for resolution-independent inference, enabling the processing of high-resolution images without increasing memory or computational requirements. The project includes a synthetic dataset generator that creat

VDO.Ninja is a low-latency peer-to-peer media routing service and video streaming platform designed to integrate remote audio and video feeds into professional production workflows. It functions as a WebRTC broadcast integration tool and studio controller, allowing for the direct transmission of high-definition media between publishers and viewers with minimal delay. The platform distinguishes itself through extensive protocol bridging, converting between WebRTC, WHIP, WHEP, SRT, and RTMP to ensure compatibility across diverse network environments and professional studio software. It includes

BiRefNet is a PyTorch image segmentation framework designed for high-precision binary mask generation. It functions as a bilateral image segmentation model used to isolate foreground objects from complex backgrounds, as well as a specialized tool for camouflaged object detection and industrial defect detection. The project is designed for export to the ONNX format, which facilitates cross-platform deployment and inference. It supports custom model fine-tuning on user-provided image and mask datasets to adapt the model for specialized professional use cases. The system covers high-resolution

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

This project is a comprehensive software suite for voice synthesis and model management, providing a framework for training custom acoustic models and performing voice conversion. It utilizes deep-learning-based acoustic modeling to map source audio characteristics to target voice identities, enabling the transformation of input audio into specific vocal profiles. The system distinguishes itself through a feature-retrieval-based inference mechanism, which employs vector index files to perform nearest-neighbor searches on acoustic features for high-fidelity timbre matching. Users can manage th

Hallo is an audio-driven talking head generator and portrait animation framework. It synchronizes a static portrait image with an audio file to produce realistic talking head videos by mapping audio spectral features to facial expressions and lip movements. The system utilizes a diffusion video synthesis model that employs iterative denoising and latent representations to generate temporally consistent video frames. It incorporates identity-preserving feature extraction and latent space motion modeling to maintain visual consistency and control facial poses. The toolkit provides capabilities

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

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

Real-Time-Person-Removal is a web-based computer vision application designed to identify and remove human figures from live video streams. Using TensorFlow.js, the tool functions as a real-time background subtraction system that analyzes scene composition to isolate static backgrounds from moving people. The project enables browser-based computer vision by processing webcam video feeds directly in the client. It utilizes machine learning to differentiate between dynamic scene elements and the background, allowing for the real-time removal of people from the visual field.

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

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

quaggaJS is a JavaScript barcode scanner library and client-side processor that performs barcode localization and decoding directly within the browser. It functions as a computer vision barcode decoder that extracts data from both static image files and live camera streams without requiring external server requests. The library supports real-time barcode scanning via webcams and can detect multiple barcode formats simultaneously. It includes tools to visualize the decoding process by rendering bounding boxes and scanlines over the image to monitor localization. Users can configure the specif

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

libfacedetection is a C++ face detection library and computer vision tool. It utilizes a neural network face detector to identify human faces in images and return bounding box coordinates. The library is designed for low latency and high throughput processing, enabling real-time face detection in image and video streams. It supports automated image analysis for identifying coordinates of human faces across large batches of photos and high-performance video processing.

Hallo2 is an AI video generation tool and audio-driven portrait animation framework designed to transform static images into speaking videos. It functions as a portrait image animator that synchronizes a single photo with an audio track to produce high-resolution talking head videos. The system includes a distributed animation trainer for fine-tuning deep learning models using custom datasets and distributed computing resources. It employs hierarchical video generation and temporal consistency modeling to produce long-form character animations that remain stable over extended durations. The

This project is a web-based graphic design editor and online poster designer. It provides a browser-based environment for creating professional visual layouts, e-commerce graphics, and social media covers using a canvas with drag-and-drop elements. The toolkit includes a specialized PSD template converter that parses Photoshop design files into editable web templates. It also features a custom QR code generator capable of producing styled codes with gradients and embedded logos, alongside a browser-based image manipulation tool for cropping assets and removing backgrounds. The editor covers

RapidRAW is a non-destructive RAW photo editor and digital asset manager designed for decoding manufacturer RAW formats and applying tonal and color adjustments. It functions as a professional image processor that ensures original source data remains unmodified by saving all edits, masks, and crops to sidecar files. The software features a specialized color grading suite using 3D LUTs, color wheels, and HSL mixers, alongside AI-powered utilities for subject isolation, automatic masking, and generative inpainting for object removal. It distinguishes itself with AI-assisted photo retouching and

Flowblade is a non-linear video editor and multitrack video compositor. It provides a professional environment for composing multitrack timelines, trimming media clips, and managing assets through a visual effects processing engine. The project distinguishes itself with a hardware-synced playback controller that allows for manual scrubbing using external USB shuttle and jog devices. It also includes a hardware-accelerated video encoder that utilizes CPU and GPU acceleration to render project timelines into final formats. The software covers a broad range of production capabilities, including