Imaginaire este o bibliotecă PyTorch pentru sinteza imaginilor și un framework de traducere neuronală a imaginilor, conceput pentru a genera conținut vizual sintetic de înaltă rezoluție. Funcționează ca un generator vizual de deep learning care mapează imagini și videoclipuri semantice în versiuni fotorealiste, folosind atât metode supervizate, cât și nesupervizate.
Principalele funcționalități ale nvlabs/imaginaire sunt: Deep Learning Image Translators, Multi-Domain Synthesis, Example-Guided Generation, Unsupervised Style Translation, Synthetic Content Generators, Image Synthesis Libraries, Paired Image Translation, Unpaired Image Translation.
Alternativele open-source pentru nvlabs/imaginaire includ: yunjey/stargan — StarGAN is a PyTorch image-to-image translation framework designed to synthesize visual styles and attributes across… taki0112/ugatit — UGATIT is an unsupervised generative adversarial network and image-to-image translation model implemented in… phillipi/pix2pix — pix2pix is a framework for image-to-image translation using conditional generative adversarial networks. It functions… junyanz/cyclegan — CycleGAN is a generative adversarial network framework designed for unpaired image-to-image translation. It enables… paddlepaddle/paddlegan — PaddleGAN is a generative AI framework and deep learning computer vision library built on the PaddlePaddle framework.… junyanz/pytorch-cyclegan-and-pix2pix — This project is a deep learning framework designed for training and deploying image-to-image translation models. It…
UGATIT is an unsupervised generative adversarial network and image-to-image translation model implemented in TensorFlow. It serves as the official research implementation of an ICLR 2020 paper, providing a framework for converting images between different visual styles without requiring paired training examples. The system utilizes an unsupervised generative attentional network and attention maps to deform geometric shapes and modify textures during the translation process. It employs a cycle-consistent framework to ensure translation quality by requiring images to return to their original st
StarGAN is a PyTorch image-to-image translation framework designed to synthesize visual styles and attributes across multiple domains. It implements a generative adversarial network that serves as a deep learning image translator for modifying specific visual characteristics within an image dataset. The framework uses a single unified model to handle translations between multiple image domains rather than requiring separate pairs of models. It is a research implementation that learns mappings between different image attributes without the need for paired training data. The project covers the
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
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