Actualités

Fonds2 a
Firefly, l'IA « text to image » d'Adobe, entre instantanément dans la cour des grands
Projet DraGAN Nous avons pu tester en avant-première le « text to image » d'Adobe et sommes restés pantois. Il ouvre la voie à de très belles images obtenues de façon aisée. Et à d'autr ...
IEEE2 a
Autoencoder Image Denoising to Increase Optical Character Recognition Performance in Text Conversion
Our research aims to build an autoencoder for denoising text images and evaluate the OCR’s performance in converting the denoised image into text. The first step in the research is to test the OCR ...
GitHub2 a
AutoEncoder-based Image Retrieval System - GitHub
In this project, I have built an image retrieval system using the AutoEncoder neural network. The network was trained with the CIFAR-10 dataset. The hyperparameters for training the model are provided ...
GitHub1 a
Generate Images from text prompt using Stable Diffusion Model
We used a pre-train variational autoencoder (vae: has an encoder and decoder ... References: How and why stable diffusion works for text to image generation ...
IEEE1 a
FaceCLIP: Facial Image-to-Video Translation via a Brief Text Description
Abstract: The existing image-to-video translation methods generally follow ... We design a reconstruction loss and an embedding alignment loss to train the autoencoder to obtain the text-guided video ...
unite2 a
Microsoft Proposes GODIVA, a Text-To-Video Machine Learning Framework
GODIVA uses the Vector Quantised-Variational AutoEncoder (VQ-VAE ... OpenAI's CLIP framework is capable of zero-shot matching of images to text, as well as facilitating image synthesis by reversing ...
Frontiers1 a
A blind convolutional deep autoencoder for spectral unmixing of hyperspectral images over waterbodies
and their abundance maps for each ROI are selected in the HSI2 image. Finally, we propose the best configuration and settings for the hyperparameters. The main contributions are summarized as follows: ...
Frontiers2 a
Learning the heterogeneous representation of brain's structure from serial SEM images using a masked autoencoder
We randomly masked voxels in three-dimensional brain image patches and trained an autoencoder to reconstruct the neuronal structures. Results and discussion: We tested different pre-training and ...