137 datasets found

ProGAN and LSUN are used as training datasets for the FakeInversion model.

Masked diffusion transformer is a strong image synthesizer.

Face aging is an ill-posed problem because multiple plausible aging patterns may correspond to a given input. Most existing methods often produce one deterministic estimation....

The dataset used for training and evaluation of the W¨urstchen model.

The dataset used for training and evaluation of the W¨urstchen model.

Progress in GANs has enabled the generation of high-res-olution photorealistic images of astonishing quality. StyleGANs allow for compelling attribute modification on such...

The Visual Genome dataset is a large-scale visual question answering dataset, containing 1.5 million images, each with 15-30 annotated entities, attributes, and relationships.

A dataset of WiFi CSI and corresponding image time series for through-wall image synthesis

The dataset used for training and validation of the proposed approach to combine semantic segmentation and dense outlier detection.

The CLIP model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be...

The dataset used for calibration during the quantization process.

This dataset is used in the paper to demonstrate the effectiveness of the GANSpace technique.

The dataset used in the paper for training and testing the proposed method for detecting, attributing and localizing GAN generated images.

High-fidelity image synthesis using Generative Adversarial Networks (GANs).

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

The LLFF dataset contains 8 forward-facing scenes. Following [19, 26, 35, 42], we take every 8-th image as the novel views for testing. The input views are evenly sampled across...