Open-source alternatives to Deep Painterly Harmonization

This project is a TensorFlow-based neural style transfer tool and deep learning image processor. It uses convolutional neural networks to apply the artistic style of one image to the content of another through neural image synthesis. The system supports multi-style blending to combine artistic characteristics from several different images into a single output. It also includes color-preserving stylization, which maintains the original color palette of the source image by merging source color data with the luminance of the stylized result. The tool provides capabilities for style abstraction

Grade is a JavaScript library for image color analysis and dynamic theme generation. It extracts the most prominent colors from an image to automatically generate complementary CSS gradients and coordinated color palettes for web interfaces. The tool identifies dominant colors using pixel-data analysis and applies mathematical offsets to determine matching hues. It can inject these calculated values directly into the document as CSS custom properties or export the gradient data as a raw array for custom visual implementation.

Pywal is an image-based theme engine and dynamic color scheme generator that extracts dominant colors from images to create coordinated system-wide color palettes. It functions as a cross-application theme synchronizer and terminal color palette manager, updating interface colors and environment configurations in real-time. The system synchronizes generated palettes across third-party software, window managers, and supported hardware, including RGB backlight controllers for keyboards and laptops. It integrates wallpaper management by applying a source image as the system background while simu

Color-thief-py is a Python library designed to analyze digital images for the purpose of extracting prominent color information. It functions as a computer vision tool that processes image files to identify the single most dominant color or to generate a representative color palette based on the visual composition of the source. The library utilizes the Pillow imaging library to handle diverse file formats and load image data into memory as structured pixel arrays. By mapping these pixels into a three-dimensional color space and applying median-cut quantization, the tool identifies statistica

DeepDream is a deep learning image processor and convolutional neural network art generator designed to synthesize psychedelic imagery and visualize how neural networks interpret visual data. It functions as a tool for generating generative AI art by amplifying patterns recognized by a pre-trained model to produce dream-like effects. The project utilizes a TensorFlow image visualizer to explore how different layers of a neural network perceive images. This is achieved through algorithmic image manipulation and deep learning visualization techniques that transform standard photographs into sty

DeOldify is a deep learning system and a set of pre-trained computer vision models designed to apply realistic colors to grayscale photographs and video footage. It functions as a neural media restoration tool that uses trained networks to estimate original hues for black-and-white media and remove glitches and artifacts from aged images and film. The project employs a NoGAN colorization technique that removes the GAN discriminator during training to prevent artifacts and avoid over-saturation of pixels. For cinematic sequences, it applies temporal frame consistency to maintain color stabilit

Color-thief is a color quantization library and image color palette extractor designed to identify the most prominent colors in visual media. It functions as a semantic color classifier and color space converter, providing tools to extract dominant colors and generate representative palettes from images, videos, and canvas elements. The project utilizes a WebAssembly color processor and background workers to perform high-performance pixel analysis. It implements a WCAG contrast analyzer to calculate color contrast ratios and determine accessible foreground text colors based on accessibility s

Clarity-upscaler is an AI image upscaler and enhancement tool that uses deep learning models to increase image resolution and restore visual detail. It functions as a super-resolution inference engine that employs neural networks to predict missing pixels and synthesize high-frequency details from low-resolution sources. The project is delivered as a programmable API, allowing the integration of automated high-resolution image processing and sharpening into external applications and workflows. This interface enables the programmatic upscaling of images to create high-resolution assets. The s

This project is an AI upscaling framework and deep learning image restorer designed to estimate original source pixels from low-resolution inputs. It functions as a super-resolution reconstruction system that transforms pixelated images into high-resolution versions by restoring high-frequency details and sharpening edges. The system utilizes a convolutional neural network pipeline to analyze pixel data and perform digital image restoration. It employs pixel-shuffle upsampling to rearrange channel dimensions into spatial dimensions, which increases resolution while reducing checkerboard artif

Chameleon is a color framework for Swift and Objective-C applications, providing a toolkit for managing dynamic palettes, gradient libraries, and hexadecimal conversions. It functions as a system for creating harmonious color schemes and calculating contrasting text colors based on background luminance. The project includes an image color extractor that analyzes images to generate matching color schemes or calculate average colors for user interfaces. It also features a gradient color library for creating and applying smooth transitions to backgrounds and text elements. The framework covers

Chameleon is a color framework for Swift and Objective-C applications. It provides systems for programmatic color palette generation, global theme orchestration, hexadecimal conversion, and the extraction of visual data from images. The library includes a dynamic theme engine for applying global visual styles and luminance adjustments across an interface. It features a palette generator for creating analogous, complementary, and triadic color schemes based on a seed color, and an image color extractor to derive average colors or palettes from images. The framework covers a range of color man

Style2paints is a deep learning image processor designed for the automated colorization of grayscale line art. It functions as a generative style transfer engine that maps artistic color palettes and textures onto monochrome sketches, allowing users to transform black and white drawings into finished illustrations through neural network inference. The system distinguishes itself by incorporating user-provided color guidance and style references to influence the final output. It utilizes coordinate-mapped color points and hint-driven optimization to ensure that specific colors are applied prec

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

This project is an academic curriculum repository and educational resource center for studying probability, statistics, and machine learning. It serves as a deep learning course website and a hub for instructional materials, providing a structured collection of content designed to teach neural network architectures. The repository distinguishes itself by combining a comprehensive educational resource with a machine learning project archive. It provides a curated set of research examples and implementation guides for a wide range of models, including multilayer perceptrons, convolutional netwo

This project is a QML desktop shell designed for desktop environment orchestration and interface customization. It functions as a system status dashboard and a declarative user interface for managing system hardware, window metadata, and user sessions. The shell features a dynamic theme generator that extracts dominant colors from wallpapers to automatically synchronize the global visual color palette. It utilizes an inter-process communication system to orchestrate shell functions and a hierarchical JSON configuration framework to manage global and per-monitor interface layouts. The system

Gluon-CV is an MXNet computer vision library that provides a comprehensive collection of pre-implemented vision architectures and training pipelines. It serves as a deep learning research toolkit and a model zoo containing state-of-the-art pre-trained weights for image and video analysis. The project includes a specialized human pose estimation library and a model compression toolkit. These tools allow for the pruning and quantization of deep learning models to increase inference speed and facilitate deployment on constrained edge hardware. The library covers a broad range of vision capabili

This project is a PyTorch implementation of a research architecture designed for high-resolution representation learning. It serves as a computer vision framework focused on precise keypoint detection, human pose estimation, and semantic image segmentation. The implementation provides specialized tools for identifying anatomical landmarks on the human body and predicting facial keypoint coordinates to analyze orientation and alignment. It utilizes a system of multi-resolution parallel streams and repeated multi-scale fusion to maintain high-resolution representations throughout the network.

DenseNet is a computer vision model and convolutional neural network implementation designed for image recognition and classification tasks. It utilizes a densely connected network architecture where each layer is connected to every other layer to improve feature propagation. The implementation reduces the number of parameters while maintaining accuracy through a dense-connectivity pattern and layer-aggregation concatenation. It supports model construction using both standard and bottleneck-compressed architectures, with configurable network depth and growth rates to balance inference time an

Anime-InPainting is a specialized software platform designed for the restoration of anime illustrations and digital artwork. It functions as a deep learning-based image editor that utilizes generative models to repair damaged or incomplete images, remove unwanted artifacts, and eliminate visual blemishes such as mosaics. The project distinguishes itself through an edge-guided generative approach, which uses structural edge maps to ensure that reconstructed regions maintain visual and spatial consistency with the surrounding image. Users can interact with the restoration process through a grap

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

Thumbhash is an image encoding library that converts images into compact strings to be used as lightweight placeholders. This format provides a binary representation of an image that preserves color and aspect ratio, allowing for the generation and rendering of blurred previews during page loads. The project serves as an alternative to Blurhash by providing a method to encode images into tiny strings while avoiding high-frequency computational overhead. It also functions as a color palette extractor, enabling the derivation of the dominant average RGB color from an encoded representation for

mdui is a framework-agnostic UI library and design system based on Material Design 3 standards. It provides a comprehensive set of reusable interface elements implemented as native Web Components, ensuring compatibility across different JavaScript frameworks. The library features a sophisticated theming system that supports light and dark modes, as well as the ability to generate dynamic color palettes from seed colors or image sources. It distinguishes itself with a high level of flexibility in visual customization, using CSS custom properties to control design tokens such as typography, cor

This project is a collection of optional, community-contributed algorithms and specialized vision tools that extend the core OpenCV framework. It serves as a comprehensive library of extra modules for computer vision research, providing advanced toolsets for image processing, visual data analysis, and object detection. The library includes specialized frameworks for augmented reality tracking, biometric face recognition, and three-dimensional pose estimation. It provides distinct capabilities for identifying AR markers, tracking 3D object silhouettes, and performing neural network vulnerabili

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

Scenic is a research framework designed for the development and training of deep learning models, with a specific focus on computer vision and multimodal transformer architectures. It provides a comprehensive toolkit for defining neural network structures, managing large-scale data pipelines, and executing training workflows across distributed hardware environments. The framework is built upon a functional programming paradigm that utilizes hardware-agnostic tensor abstractions and just-in-time compilation to maximize computational efficiency. By employing modular layer composition, it allows

Vim is a state space model vision framework designed for image classification and visual representation learning. It functions as a computer vision research tool that converts two-dimensional image grids into one-dimensional sequences to extract spatial features. The system implements a linear-scaling image classifier that replaces quadratic attention mechanisms with state space operations. This approach utilizes bidirectional sequence modeling and selective gating mechanisms to process visual data. The framework covers computer vision benchmarking and image classification research, providin

FairMOT is a multi-object tracking framework and deep learning model designed to identify and track multiple entities across video frames. It implements a unified pipeline that integrates object detection and identity re-identification into a single-stage joint network. The system utilizes an anchor-free detection method to predict object centers and bounding box dimensions. It maintains identity consistency across consecutive frames by generating high-dimensional embedding vectors for re-identification and employing a Kalman filter for motion state prediction. The framework covers a broad r