🌱 SNE-RoadSeg in PyTorch, ECCV 2020 by Rui (Ranger) Fan & Hengli Wang, but now we have improved it.

Unofficial CycleGAN Implementation for our CS484 course project at Bilkent University

Image-to-Image Translation in PyTorch

Task: Neural Style Transfer. The implemented solution uses a CycleGan architecture.

Artificial Intelligence

An end-to-end signature verification system to extract, clean and verify signatures in documents. Signatures are detected using YOLOv5. Noise is cleaned using a CycleGAN approach and verified. Keras / Tensorflow / PyTorch

Seminar project Unsupervised Image-to-Image translation using GANs

PyTorch Implementation of paper titled "D2BGAN: A Dark to Bright Image Conversion Model for Quality Enhancement and Analysis Tasks Without Paired Supervision"

CycleGAN for Scenery to Pixel Art Generation

ICASSP 2024. A Parameterized Generative Adversarial Network Using Cyclic Projection for Explainable Medical Image Classification.

Code for Dual Contrastive Learning for Unsupervised Image-to-Image Translation, NTIRE, CVPRW 2021, oral.

Collection of my R&D works and implementations in my Airbus Master Thesis

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

This repository contains the GAN programs that we implemented for the TCIRRP dataset as part of mini project in university.

Style Transfer Using Generative Adversarial Networks for Brain MRI Enhancement

Final project from DLS course

Project based on Neural Style Transfer, implemented using a CycleGan architecture

In this project, we aim to leverage the power of artificial intelligence (AI) to generate paintings inspired by Vincent van Gogh's iconic works. Specifically, we will explore the use of a cycle generative adversarial network (CycleGAN) to generate new artworks that capture the essence of Van Gogh's style.

Pix2Pix and CycleGAN training code