StarGAN v2 - Official PyTorch Implementation (CVPR 2020)
CycleGAN is a generative adversarial network framework designed for unpaired image-to-image translation. It enables the conversion of images between two distinct visual domains using datasets that do not require direct one-to-one matching examples. The project implements a deep learning style transfer tool capable of artistic style transfer, object transfiguration, and domain-to-domain conversion. It uses a dual-generator architecture and cycle-consistency loss to ensure that images translated to a target domain and back recover their original state. The framework covers core machine learnin
PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
Die Hauptfunktionen von chuanli11/mgans sind: Domain Transfer and Translation.
Open-Source-Alternativen zu chuanli11/mgans sind unter anderem: carpedm20/discogan-pytorch — PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks". clovaai/stargan-v2 — StarGAN v2 - Official PyTorch Implementation (CVPR 2020). fxia22/pixeldtgan — A torch implementation of "Pixel-Level Domain Transfer". junyanz/cyclegan — CycleGAN is a generative adversarial network framework designed for unpaired image-to-image translation. It enables… luanfujun/deep-photo-styletransfer — This project is a deep learning style transfer framework designed to apply artistic styles to photographs. It… nvlabs/munit — Multimodal Unsupervised Image-to-Image Translation.
