328 Open source projects that are alternatives of or similar to traiNNer

AI无损放大工具

A Real-ESRGAN model trained on a custom dataset

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

SwinIR: Image Restoration Using Swin Transformer (official repository)

(ECCV 2020) Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration

PyTorch implementation of GANs (Generative Adversarial Networks). DCGAN, Pix2Pix, CycleGAN, SRGAN

This is the project page of our paper which has been published in ECCV 2020.

Image Deblurring using Generative Adversarial Networks

Quake 2 textures upscaled using ESRGAN and the Manga109Attempt model

MATLAB implementations of Generative Adversarial Networks -- from GAN to Pixel2Pixel, CycleGAN

TensorFlow code for ECCV 2018 paper "Image Super-Resolution Using Very Deep Residual Channel Attention Networks"

Setup scripts for ESRGAN/MXNet image/video upscaling in VapourSynth

This is the source code of PMHLD-Patch-Map-Based-Hybrid-Learning-DehazeNet-for-Single-Image-Haze-Removal which has been accepted by IEEE Transaction on Image Processing 2020.

[NeurIPS 2018] Visual Object Networks: Image Generation with Disentangled 3D Representation.

PyTorch (and PyTorch Lightning) implementation of Neural Style Transfer, Pix2Pix, CycleGAN, and Deep Dream!

Open source single image super-resolution toolbox containing various functionality for training a diverse number of state-of-the-art super-resolution models. Also acts as the companion code for the IEEE signal processing letters paper titled 'Improving Super-Resolution Performance using Meta-Attention Layers’.

Video, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, SRMD, RealSR, Anime4K, RIFE, CAIN, DAIN, and ACNet.

wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch

High-Dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.

DEPRECATED: Depth Map Estimation from Monocular Images

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

[CVPR 2020] GAN Compression: Efficient Architectures for Interactive Conditional GANs

Official Python implementation of the 'Sparse deconvolution'-v0.3.0

Image-to-Image Translation in PyTorch

Simple and extensible GAN image-to-image translation framework. Supports natural and medical images.

Voice Conversion by CycleGAN (语音克隆/语音转换): CycleGAN-VC2

A Conditional Generative Adverserial Network (cGAN) was adapted for the task of source de-noising of noisy voice auditory images. The base architecture is adapted from Pix2Pix.

Keras Implementation of MIRNet - SoTA in Image Denoising, Super Resolution and Image Enhancement - CVPR 2020

TensorRT Examples (TensorRT, Jetson Nano, Python, C++)

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

Official TensorFlow code for paper "Multi-Image Super Resolution of Remotely Sensed Images Using Residual Attention Deep Neural Networks".

[TPAMI 2020] Parallax Attention for Unsupervised Stereo Correspondence Learning

A minimal tensorflow implementation of pix2pix (Image-to-Image Translation with Conditional Adversarial Nets - https://phillipi.github.io/pix2pix/).

[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

Colorization of grayscale images using CycleGAN in TensorFlow.

Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution

SRZoo: An integrated repository for super-resolution using deep learning

VapourSynth Single Image Super-Resolution Generative Adversarial Network (GAN)

VAE with RealNVP prior and Super-Resolution VAE in PyTorch. Code release for https://arxiv.org/abs/2006.05218.

Bicubic interpolation for images (Python)

PyTorch implementation of Image-to-Image Translation with Conditional Adversarial Nets (pix2pix)

Pytorch implementation for SRDenseNet (ICCV2017)

Manual, source-code and binaries for the NanoJ-Fluidics project

NTIRE 2020 NonHomogeneous Dehazing Challenge (CVPR Workshop 2020) 1st Solution.

The project is the official implementation of our CVPR 2021 paper, "Restoring Extremely Dark Images in Real Time"

Use keras.js and cyclegan-keras to colorize manga automatically. All computation in browser. Demo is online:

[CVPR 2021] Exploring Sparsity in Image Super-Resolution for Efficient Inference

Generative Adversarial Network for single image super-resolution in high content screening microscopy images

Pytorch implementation of BicycleGAN with implementation details

Deep Learning Super Sampling with Deep Convolutional Generative Adversarial Networks.

Denoise of ECG signal with machine learning

DeepSUM: Deep neural network for Super-resolution of Unregistered Multitemporal images (ESA PROBA-V challenge)

Official repository of "Deep Coupled Feedback Network for Joint Exposure Fusion and Image Super-Resolution"

Tensorflow implementation of the NIPS paper "Toward Multimodal Image-to-Image Translation"

Automatically apply AI Upscaling on Dumped Textures

Semantic Image-to-Image Translation for Domain Adaptation

A survey of recent application of deep learning on super-resolution tasks

An easy way to use anime4k in python

This is a pix2pix demo that learns from edge and translates this into view. A interactive application is also provided that translates edge to view.