Projects sharing features with Fast Neural Style

This project is a deep learning style transfer framework designed to apply artistic styles to photographs. It functions as a photorealistic image stylizer that merges the content of one image with the visual characteristics of another while maintaining the original geometry and structural details. The system distinguishes itself through the use of matting Laplacian matrices and semantic segmentation masks to prevent distortion and preserve edge fidelity. These capabilities allow for region-specific styling, where different aesthetics can be applied to distinct objects or areas within a single

AnimeGANv2 is a generative adversarial network training framework and image stylization tool designed to convert real-world photographs and videos into anime-style imagery. It functions as an anime style generator that transforms real-world scenes into animation through supervised style transfer. The project provides a system for training style models and extracting specific generator weight parameters from deep learning checkpoints to create lightweight models for inference. It focuses on landscape image stylization and the ability to mimic specific artistic styles from provided datasets. T

PerceptualSimilarity is a deep learning framework designed to quantify and evaluate the perceptual distance between images. It provides a system for measuring how similar two images or image patches appear to human vision by using deep feature representations instead of pixel-wise differences. The project implements a differentiable distance metric that functions as a loss function, allowing image pixels to be optimized via backpropagation to reach a target visual appearance. It includes a trainable linear layer that can be applied to frozen deep features to learn weighted distance metrics al

This project is a deep learning library built for single-image super-resolution and visual enhancement. It provides a framework for training and deploying neural network architectures designed to reconstruct high-resolution images from low-resolution sources, effectively recovering fine details and removing artifacts caused by downscaling or compression. The library distinguishes itself through the implementation of generative adversarial networks and residual block architectures, which work together to improve the realism and clarity of upscaled outputs. It supports training through both pix

This project is a structured TensorFlow deep learning curriculum and an interactive machine learning course delivered through Jupyter Notebooks. It serves as a technical guide and model zoo providing reference implementations for neural networks and machine learning algorithms. The curriculum focuses on practical implementations of computer vision, including object detection, semantic segmentation, and style transfer. It also provides tutorials for natural language processing, specifically covering word embeddings and encoder-decoder architectures for sequence modeling. The material covers t

Triangula is a genetic algorithm image stylizer and renderer that transforms raster images into stylized polygonal artwork. It functions as an image-to-SVG converter that optimizes point placement to recreate the shapes and colors of a source image using triangulated polygons. The project utilizes a fitness-based point selection process and genetic algorithm optimization to iteratively evolve vertex positions. This approach minimizes the difference between the generated polygons and the original image through crossover, mutation, and iterative polygon refinement. The system covers the full p

This is a PyTorch CNN visualization toolkit designed for neural network interpretability. It provides a set of tools to explain model decisions and analyze the internal behavior of convolutional neural networks through the visualization of activations, gradients, and filters. The project implements specialized techniques for synthesizing representative images, including Deep Dream optimizations to amplify patterns and class-specific image generation via input optimization. It also features a saliency map generator that produces gradient-based heatmaps to identify the specific image regions in

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

This project is an unsupervised image restoration tool that uses a convolutional neural network as a structural prior to reconstruct images from noisy or incomplete data. It functions as a neural network image prior, utilizing the inherent biases of the network architecture to restore pixels without the need for a pre-trained dataset or external learning. The system performs zero-shot image restoration by treating the network architecture itself as a regularization term. It uses a randomly initialized encoder-decoder structure and iterative gradient descent to minimize pixel-wise loss, recove

DragGAN is an interactive generative image editor and manipulator that allows users to reshape visual output by moving handle points on a generative network manifold. It functions as a tool for point-based image editing, mapping user-defined coordinate shifts to a generative model's latent space to deform images. The system includes a generative image inversion tool that converts real photographs into latent representations. This process enables the interactive manipulation of non-generated content by bringing real-world images into a compatible format for the generative adversarial network.

This is a PyTorch implementation of a neural style transfer system. It functions as a convolutional neural network image stylizer and artistic style blender designed to combine the content of one image with the artistic style of another. The system supports blending multiple style sources and adjusting the relative weights between content and style reconstruction. It includes capabilities for preserving the original color palette of the content image and adjusting style scales to determine which artistic patterns are transferred. The pipeline enables high-resolution image processing by distr

Paints-UNDO is an AI-driven system designed to reverse final digital images into simulated brush stroke sequences. It functions as a digital art undo simulator and a drawing sequence reconstructor, predicting and visualizing previous states of a painting by reversing artistic operations. The project transforms static images into process videos by interpolating between reconstructed drawing states. It uses an image-to-video painting process generator to create smooth progression videos of artwork. The system covers digital art reconstruction and artistic process simulation, including the abil

This project is a collection of deep learning tutorials and practical implementations using TensorFlow. It provides a neural network implementation guide through code examples designed for research-oriented deep learning. The repository covers supervised and unsupervised learning workflows, including the development of sequence models for language processing and chatbots. It includes specific examples for image style transfer and the use of autoencoders for feature extraction. The project also provides demonstrations for managing large-scale datasets using binary record formats and streaming

This repository collects illustrated single-page cheat sheets that compress the core topics of Stanford's CS 230 deep learning course into visual reference summaries. The collection covers convolutional neural networks, recurrent neural networks, and practical training techniques, pairing schematic diagrams with mathematical notation to bridge intuition and formal understanding. The cheat sheets are organized by subject area and link related concepts across topics, such as connecting vanishing gradients to LSTM gates, to reinforce the full deep learning workflow. Practical training advice on

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

This project is a collection of structured study notes and notebooks serving as an educational resource for deep learning and neural network fundamentals. It provides a technical reference for implementing machine learning theory, covering everything from basic network design to the construction of advanced architectures. The material specifically focuses on the implementation of convolutional neural networks for computer vision and sequence models for natural language processing. It includes detailed guidance on building object detection systems, face recognition, and speech transcription mo

This project is a diffusion-based AI art generator and animation framework used to create digital images and motion graphics from text prompts. It functions as a system for producing stylized videos and AI art through iterative diffusion sampling and neural network models. The framework distinguishes itself through specialized tools for 3D depth animation, using depth-map transformations to create spatial movement. It also includes neural style transfer capabilities to apply specific artistic looks, such as watercolor or pixel art, and utilizes optical flow frame blending to reduce flickering

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

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

Dot is a deep learning face swap tool used to replace faces in live video streams, recorded media, and static images. It functions as a deepfake media processor and real-time video manipulator that applies facial transformations through neural network mapping. The system includes a virtual camera video injector that routes processed output into a system-level virtual device to simulate a physical hardware webcam. This allows generated video to be used within third-party video conferencing software. The tool supports real-time source switching via keyboard inputs to toggle between different s

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

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

Headtrackr is a JavaScript library and computer vision face tracker designed to monitor head position and orientation via a webcam. It provides a head tracking API that detects face location and spatial coordinates within a live video stream to create head-coupled perspective effects. The project functions as a tool for shifting 3D rendering perspectives in real time based on physical head movements. It utilizes WebRTC and media stream integration to capture video data and identify a user's face and rotation within a web browser. The library covers computer vision capabilities for face and h

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

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

Gifify is a tool for converting video files into optimized animated GIFs. It functions as a video to GIF converter and optimization utility that extracts specific clips from video files and burns text or subtitle overlays directly into the frames. The project differentiates itself through specialized GIF optimization, using lossy compression, color count limiting, and custom color palette generation to reduce file sizes. It also provides precise control over the output by allowing users to adjust playback speed, reverse playback direction, and resize dimensions. The software covers a broad s