190 datasets found

The authors used a dataset of 1000 images, each consisting of three randomly selected MNIST digits.

The dataset used in the paper for testing the proposed Data-Independent Operator (DIO) framework for generalizable forgery image detection.

The dataset is a subset of Extreme UltraViolet (EUV) images from the SDO AIA instrument, used for high resolution solar observation imaging.

The dataset used in the paper is a synthetic MNIST dataset generated by forming barycenters constructed with weights sampled uniformly from ∆3.

The dataset used in this paper for image generation.

SinGAN is a new unconditional generative model that can be learned from a single natural image.

Wasserstein Auto-Encoder (WAE) is a generative model that uses a combination of convolutional and fully connected layers to learn a probabilistic representation of images.

The dataset used in the paper is the LSUN bedrooms dataset, a large-scale image dataset.

The proposed framework generates JPEG compressed images using generative adversarial networks.

The LRS2 dataset consists of 48,164 video clips from outdoor shows on BBC television. Each video is accompanied by an audio corresponding to a sentence with up to 100 characters.

A large-scale dataset for generalizable and robust synthetic image detection, comprising diverse generators, object categories, and real-world challenges.

The InfiMNIST dataset is a synthetic dataset of MNIST-like images.

High-resolution images of bedrooms.

High-resolution images of churches.

The dataset used in this paper is a collection of images generated by different Generative Adversarial Networks (GANs). The dataset is used to evaluate the performance of GANs...

Conditional image generation has paved the way for several breakthroughs in image editing, generating stock photos and 3-D object generation.

The DDPM dataset consists of data from 86 subjects attempting to answer questions deceptively. Interviews were recorded at 90 frames-per-second for more than 10 minutes on average.

Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage...

The dataset contains images of subjects and styles, used for training and testing the FreeTuner model.

FreeTuner is a training-free method for compositional personalization that can generate any user-provided subject in any user-provided style.