There are 7 repositories under perceptual-losses topic.
LPIPS metric. pip install lpips
StyleGAN Encoder - converts real images to latent space
StyleGAN Encoder - converts real images to latent space
Single Image Reflection Separation with Perceptual Losses
[ACM MM 20 Oral] PyTorch implementation of Self-supervised Dance Video Synthesis Conditioned on Music
ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks, published in ECCV 2018) implemented in Tensorflow 2.0+. This is an unofficial implementation. With Colab.
PyTorch implementation of the Perceptual Evaluation of Speech Quality for wideband audio
Comparing different similarity functions for reconstruction of image on CycleGAN. (https://tandon-a.github.io/CycleGAN_ssim/) Training cycleGAN with different loss functions to improve visual quality of produced images
Generative Adversarial Network for single image super-resolution in high content screening microscopy images
Experiments with perceptual loss and autoencoders.
A no-reference version of HDR-VDP using deep-learning
LPIPS metric on PaddlePaddle. pip install paddle-lpips
A perceptual weighting filter loss for DNN training in speech enhancement
implement Deep Feature Consisten Variational Autoencoder in Tensorflow
A deep perceptual metric for 3D point clouds
A Study of Deep Perceptual Metrics for Image quality Assessment
Demos of neural image editing
Pytorch implementation of Neural Style Transfer (NST). Reviewing litterature and implementing some ideas.
Generate data, PSNR, Perceptual Loss, Unet
A simple and minimalistic implementation of the fast neural style transfer method presented in "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" by Johnson et. al. (2016) 🏞
Pytorch Implementation of Hou, Shen, Sun, Qiu, "Deep Feature Consistent Variational Autoencoder", 2016
Implementation of the fast neural style transfer algorithm on Keras. Includes Jupyter notebooks, python script and web app.
The implementation code of Thesis project which entitled "Photo-to-Emoji Transformation with TraVeLGAN and Perceptual Loss" as a final project in my master study.
Final assignment in the NLP course at the Technion (IEM097215). In this assignment we propose a novel architecture to handle both Text-to-Image translation and Image-to-Text translation tasks on paired data, using a unified architecture of transformers and CNNs and enforcing cycle consistency.
Investigation in 4x Super-resolution by Deep Convolutional Neural Networks
Demake-up Filter Use Unet model, Resnet50 Pretrained
single image super resolution