Awesome GitHub RepositoriesDomain Transfer and Translation

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

pix2pix is a framework for image-to-image translation using conditional generative adversarial networks. It functions as a supervised trainer and visual domain mapper designed to learn a mapping between input and output images for style and domain transfer. The system utilizes a U-Net encoder-decoder architecture combined with a PatchGAN local discriminator to enforce high-frequency local consistency. It employs L1 loss regularization to ensure generated outputs remain structurally close to the ground truth. The project covers a broad range of computer vision capabilities, including semantic

This project is a deep learning style transfer framework designed to apply artistic styles to photographs. It functions as a photorealistic image stylizer that merges the content of one image with the visual characteristics of another while maintaining the original geometry and structural details. The system distinguishes itself through the use of matting Laplacian matrices and semantic segmentation masks to prevent distortion and preserve edge fidelity. These capabilities allow for region-specific styling, where different aesthetics can be applied to distinct objects or areas within a single

StarGAN este un framework de traducere imagine-la-imagine PyTorch conceput pentru a sintetiza stiluri vizuale și atribute între mai multe domenii. Implementează o rețea generativă adversarială care servește drept traducător de imagini deep learning pentru modificarea caracteristicilor vizuale specifice într-un set de date de imagini. Framework-ul utilizează un singur model unificat pentru a gestiona traducerile între mai multe domenii de imagine, în loc să necesite perechi separate de modele. Este o implementare de cercetare care învață mapări între diferite atribute ale imaginii fără a fi nevoie de date de antrenament pereche. Proiectul acoperă antrenarea și optimizarea modelelor generative, inclusiv aplicarea checkpoint-urilor de modele pre-antrenate pentru inferență. De asemenea, oferă utilitare pentru pregătirea și organizarea seturilor de date de imagini pe baza etichetelor și a împărțirilor.

StarGAN v2 - Official PyTorch Implementation (CVPR 2020)

Multimodal Unsupervised Image-to-Image Translation

PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks

A torch implementation of "Pixel-Level Domain Transfer"