Open-source alternatives to Sensity Ai Dot

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

Rope is a graphical user interface for swapping faces in images and videos. It functions as a deepfake video editor and image face swapper that utilizes pre-trained deep learning models to replace identities in visual media. The tool includes specialized capabilities for AI video post-production, such as occlusion-aware blending to handle foreground objects and mouth-parsing refinement to align facial expressions. It also serves as an AI face restoration tool, using saliency-based restoration to recover clarity and sharpness in swapped facial regions. The software provides a pipeline for vis

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

LFLiveKit is an iOS live streaming SDK designed for capturing, encoding, and transmitting real-time audio and video streams over the RTMP protocol. The toolkit includes a hardware media encoder that uses H264 and AAC acceleration to compress streams, as well as a GPU-accelerated video filter for applying real-time beauty effects and watermarks. It also features an adaptive bitrate streamer that dynamically adjusts transmission rates and manages frame drops to maintain stability during network fluctuations. The system supports media capture from external peripheral devices and screen recordin

Yasea is an Android live streaming client used for broadcasting live camera and microphone feeds to remote servers via the RTMP protocol. It provides a system for mobile live broadcasting that integrates camera control, media encoding, and real-time network transmission. The project features GPU-accelerated video filtering to apply visual effects to live streams and a local recording system that saves a copy of the broadcast to an MP4 file while simultaneously streaming to a remote destination. It includes a camera controller for managing front and rear sensors and adjusting stream orientatio

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

SimSwap is a deep learning face swapping framework and computer vision media processor built with PyTorch. It functions as an image synthesis tool designed to replace a person's identity in images and videos with a target face using a single trained model. The system operates as a video identity replacement tool that swaps identities across frames while preserving the original expressions and lighting of the source media. It enables digital identity manipulation and the production of synthetic media through automated facial feature mapping. The framework supports both the application of trai

GPUImage2 is a Swift framework for applying real-time filters and effects to images and video using the GPU. It provides a real-time video filter library, an image geometry manipulation engine, and an OpenGL shading pipeline for processing visual data on graphics hardware. The framework enables the construction of visual effect pipelines by chaining image sources to consumers in sequential flows. It supports the development of custom fragment and vertex shaders for bespoke image processing and offers the ability to bundle these operations into reusable units via graph-based grouping. Capabil

Faceai is a computer vision toolkit designed for facial analysis, identity recognition, and image processing. It provides integrated engines for detecting human faces in static images and live video streams, matching facial encodings against identity databases, and mapping facial landmarks to understand geometric structure and alignment. The project enables real-time augmented reality applications, such as applying virtual makeup and digital accessories by scaling assets to detected facial coordinates. It also includes a suite for digital image restoration capable of removing noise, erasing w

MagicCamera is an Android camera filter SDK and face beauty library designed to provide real-time visual effects for camera and video recording applications. It serves as an image editor framework and video filter engine for enhancing facial appearance and modifying photos on Android devices. The project focuses on face beauty enhancement, specifically providing tools for skin smoothing and facial whitening. It enables the application of real-time filters to live camera streams and supports the recording of video footage with these effects applied. The system covers mobile image editing and

android-gpuimage is an OpenGL image processing library for Android that provides a GPU-powered framework for applying real-time shaders, blending layers, and processing live video streams. It functions as a real-time video filter and image blending engine to modify the luminance, vibrance, and geometry of visual content. The library enables the application of graphical effects to both static photos and live camera feeds. It supports complex image transformations, including the merging of multiple image layers through various blending modes. Capabilities cover a broad range of image manipulat

h5player is an HTML5 video player extension and web media controller that adds advanced playback controls, visual filters, and media downloading capabilities to any web page using the HTML5 video tag. It functions as a customizable media hotkey manager and real-time video filter tool to enhance the standard browser viewing experience. The project is distinguished by its configuration-driven extension system, which allows for the remapping of playback shortcuts and the addition of new features through external scripts. It also provides a real-time visual filtering suite for modifying brightnes

PRNet is a Python library for 3D facial reconstruction. It uses a deep learning regression model to predict 3D facial geometry and vertex colors from a single 2D input image to generate a textured mesh. The project provides tools for digital face swapping, allowing the replacement of a target face with a new image and blending textures to match the original pose. It also includes a framework for face texture swapping and blending to fit specific 3D poses. Additional capabilities cover facial analysis, including the detection and alignment of facial landmarks and the estimation of head pose a

MoviePy is a Python video editing library and automated video processor designed for programmatically cutting, concatenating, and manipulating video and audio files. It serves as a non-linear video editor and an interface for FFmpeg to handle the reading, writing, and conversion of diverse media formats and codecs. The library enables automated video composition through the layering of multiple video and audio streams using transparency and coordinate-based positioning. It supports dynamic content generation by inserting text overlays and performing custom video frame processing where raw fra

ByteTrack is a multi-object tracking framework that implements the ByteTrack algorithm, an ECCV 2022 method designed to recover occluded objects and reduce trajectory fragmentation. The core innovation of the project is its association algorithm, which processes every detection box—including low-confidence ones—by using separate high and low score thresholds, Kalman filter motion prediction, and Hungarian algorithm matching to produce consistent object identities across video frames. The project distinguishes itself by its comprehensive approach to handling occlusions and fragmented trajector

ShaderGlass is a GPU-accelerated shader pipeline designed to render real-time visual effects as an overlay on the desktop or specific application windows. It processes visual input through programmable fragment shaders to modify screen output or live video feeds. The project supports the import of custom shader definitions and the hot-loading of external files to test and tune visual effects without restarting. It includes a library management system for browsing presets and adjusting specific parameters to refine the final output. The application routes input from various sources, including

Gifski is a native macOS desktop application and video processing utility designed to convert video files into high-quality animated GIFs. It functions as a video-to-GIF converter that allows for the adjustment of frame rates and dimensions to balance visual fidelity with file size. The tool features capabilities for animation loop generation, including the creation of bounce effects by reversing video playback. It employs palette-based color quantization and error-diffusion dithering to maintain color accuracy and reduce banding in the final output. The application integrates with macOS sys

GPUImage is a GPU-accelerated image processing framework for iOS designed to apply real-time filters and effects to images and video. It functions as a processing engine and fragment shader library that manages textures and shaders for efficient visual data manipulation. The framework utilizes a chainable filter architecture and a texture-based data pipeline to pass image data between processing stages without expensive memory transfers. It enables the creation of bespoke visual effects through the authoring of custom fragment shaders and provides mechanisms to synchronize texture data with e

Seriously.js is a WebGL video processing framework and browser-based graphics engine designed for real-time video composition and image manipulation. It functions as a node-based visual compositor that organizes media sources and effects into a directed acyclic graph, using a custom fragment shader compiler to transform these graphs into optimized GLSL shaders for GPU-accelerated rendering. The engine features a modular web media pipeline and a plugin-based architecture, allowing for the integration of custom effects, input sources, and output targets. It enables the development of interactiv

mpv.net is a Windows graphical user interface for the mpv media player. It serves as a customizable multimedia frontend and hardware-accelerated video player that renders high-fidelity video and audio content. The project distinguishes itself by providing a searchable graphical interface for managing player settings and configuration files, alongside a themeable visual style. It supports extensibility through a scripting engine and allows for external playback management via JSON-based communication and command line interfaces. The application covers a broad range of media playback capabilit

ASCII-generator is a tool for converting images and videos into text-based ASCII art. It functions as an image-to-ASCII converter and a video-to-ASCII processor that maps pixel intensity and color to specific alphanumeric characters. The system generates stylized visual representations by transforming visual files into grayscale or colored ASCII art text files. It can render static images into text art or process video files into a sequence of ASCII art frames for animation. The rendering process involves translating image pixels into text grids and mapping brightness values to characters ba

Autocut is a text-based video editor and automatic speech recognition tool. It allows users to cut and merge video clips by modifying a text transcript instead of using a traditional timeline. The system operates as an FFmpeg video processor and subtitle manipulation utility. It converts spoken audio into text and compacts subtitle files into simplified formats, enabling the removal of unwanted video segments by deleting corresponding sentences from a transcription file. The project covers automated video transcription, non-linear video cutting, and subtitle file management. It supports hard

This project is a Stable Diffusion WebUI extension that provides a graphical interface for personalized portrait generation and AI photo editing. It allows users to train custom identity models from a small set of uploaded images to create consistent digital versions of specific people. The extension includes a virtual try-on system that replaces clothing in images by aligning reference garments with template bodies. It also features tools for face swapping in both static images and videos, as well as a portrait animator that transforms static images into dynamic videos using reference-guided

Restreamer is a self-hosted video broadcast platform and RTMP streaming server. It functions as a live media processing gateway and a multi-destination stream relay, providing a web-based management interface to configure video codecs, hardware acceleration, and stream routing. The system enables multi-platform video streaming by duplicating a single live video source and forwarding it to various third-party broadcast services and external servers simultaneously. It also supports direct-to-website broadcasting, allowing users to host live content for private or public audiences via customizab

CameraView is a high-level Android camera library and hardware wrapper designed for capturing photos and videos. It provides an abstraction layer for managing camera hardware and a media capture API for recording high-resolution video and RAW photos with configurable bitrates and resolutions. The project features a real-time camera filter framework and a preview manager. These systems allow for the application of custom shaders and visual effects to live camera streams and the rendering of previews with customizable aspect ratios, overlays, and composition grids. The library covers a wide ra

Deep-Live-Cam is a generative video transformation tool designed for real-time facial manipulation and cinematic enhancement. It functions as a local-first AI runtime, performing all media processing directly on the user's hardware to ensure complete data privacy without external network dependencies. By utilizing a high-performance processing pipeline, the application enables live face swapping and interactive video modifications during active streaming sessions or on pre-recorded media. The system distinguishes itself through a hardware-abstraction execution layer that dynamically routes co