musque's starred repositories
pytorch-CycleGAN
对pytorch-CycleGAN使用中文命名重写
CycleGAN-PyTorch
The simplest PyTorch implementation of CycleGAN.
cyclegans-demo
A demo of style transfers using CycleGAN image-to-image translation
CycleGAN_practice
图像风格迁移算法CycleGAN复现练习, 基于PyTorch
cycleGAN-PyTorch
A clean and lucid implementation of cycleGAN using PyTorch
simple_CycleGAN
a simplified pytorch CycleGAN implementation adapted from original code
CycleGANs-PyTorch
CycleGANs-PyTorch applied on Young to Old image converter.
MTCNN_face_detection_alignment
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks
Face-Alignment
Face alignment with similarity transform based on MTCNN and RetinaFace.
Face_crop_align_mtcnn
Crop and Align Face by MTCNN
Sketch-to-real-human-face-generator-iOS-Android-App
Sketch to real human face generator Android and iOS App
Sketch-Conversion---Final
We aim to convert sketches of face images to their photo realistic versions
SketchFooFE_AJS
This is the Front-End for the Sketch F00 Face Translation app.
sketch-to-face-translation
Sketch to face translation with GANs
sketch-to-face
Convert sketch to face image using Conditional Adversarial Nets (https://phillipi.github.io/pix2pix/)
face-sketch-interactivate
A project of face photo-sketch synthesis with Python which can change the synthesized sketch interactivitly.
sketch-inverso
face sketch to photo conversion using cnn
Auto_painter
Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Such an image can be generated at pixel level by learning from a large collection of images. Learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a useful application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose a model called auto-painter which can automatically generate compatible colors given a sketch. Wasserstein distance is used in training cGAN to overcome model collapse and enable the model converged much better. The new model is not only capable of painting hand-draw sketch with compatible colors, but also allowing users to indicate preferred colors. Experimental results on different sketch datasets show that the auto-painter performs better than other existing image-to-image methods.
Image-Preprocessor
Face crop, sketch to edge detection and remove dots on sketches for further processing of CycleGAN
UniversalFPSS
Universal Face Photo-Sketch Style Transfer via Multiview Domain Translation
ConditionalGAN
Convert sketch to face image using Conditional Adversarial Nets (https://phillipi.github.io/pix2pix/)
Face-Sketch-to-Image-Generation-using-GAN
Face Sketch to Image Generation using Generative Adversarial Networks
SketchToFace
Pix2Pix Image translation using conditional generative adversarial network - sketch to face