Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

awesome-neural-art

A curated list of awesome neural network-based art resources.
https://github.com/crypdick/awesome-neural-art

Last synced: 5 days ago
JSON representation

  • Background subtraction

    • Deep Image Matting paper
    • Awesome Background Subtraction
    • Dataset generator - Generates training data for the Deep Image Matting paper.
    • Tensorflow implementation - Original paper author.
    • PyTorch implementation - Same author as [Keras implementation](https://github.com/foamliu/Deep-Image-Matting), but this is their improved (and maintained) codebase.
    • Another PyTorch implementation
    • Salient Object Detection - Tensorflow implementation for cvpr2017 paper ["Deeply Supervised Salient Object Detection with Short Connections"](https://arxiv.org/abs/1611.04849) (not peer reviewed). Same author as original Deep Image Matting author.
    • AlphaGAN - Unofficial implementation of [AlphaGAN: Generative adversarial networks for natural image matting](https://arxiv.org/pdf/1807.10088.pdf). Uses a GAN as the name suggests.
    • DeepLab V3+ - Implementations of an encoder-decoder Modified Aligned Xception and ResNet as backbone [(paper)](https://arxiv.org/pdf/1802.02611.pdf).
    • PyTorch implementation - Same author as [Keras implementation](https://github.com/foamliu/Deep-Image-Matting), but this is their improved (and maintained) codebase.
  • Lectures

  • Colorization

  • Style Transfer

    • neural-style - Torch implementation of neural style algorithm.
    • adaptive-style-transfer - Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization.
    • deep-photo-styletransfer - Code and data for ["Deep Photo Style Transfer"](https://arxiv.org/abs/1703.07511).
    • fast-style-transfer - TensorFlow CNN for fast style transfer with larger scale style features in transformations.
    • texture_nets - Code for "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images".
    • AdaIN-style - Code for [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://arxiv.org/abs/1703.06868). Contains neat features such as transfering style without color, style interpolation, and spatial control.
    • Bicycle GAN - NIPS 2017 Toward Multimodal Image-to-Image Translation, PyTorch implementation. Given the same night image, model is able to synthesize possible day images with different types of lighting, sky and clouds.
    • Neural Style Transfer - Keras Implementation of Neural Style Transfer from the paper ["A Neural Algorithm of Artistic Style"](http://arxiv.org/abs/1508.06576) in Keras 2.0+.
    • Deep Painterly Harmonization - Photoshopping an object into a painting, and then neural network changes the style (pallete, strokes, luminosity, etc) of the object to match the painting style. [See paper](https://arxiv.org/abs/1804.03189).
  • Super Resolution

    • waifu2x - Image Super-Resolution for Anime-Style Art.
    • srgan - Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network.
    • fft-descreen - Clean up deconvolution checkerboard artifacts found in style transferred images.
  • Patching

    • DeepFill V1 - Generative Image Inpainting with Contextual Attention.
    • EdgeConnect - a two-stage adversarial model that comprises of an edge generator followed by an image completion network.
    • Deep Image Completion - Contains face-completion and general image completion models. Each can complete images with differnet types of corrupted masks like scribbles, lines, dots and texts.
  • Deep Dream

    • deepdream - The original Google implementation.
  • Interactive art

    • neural-doodle
    • iGAN - iGAN: Interactive Image Generation via Generative Adversarial Networks.
  • Multiple categories

    • deep-image-prior - Image restoration with neural networks but without learning. Does artifact removal, inpainting, super-resolution, denoising.