137 datasets found

Edges→Handbags dataset is a dataset of images of hands and bags.

The COCO-stuff dataset is a large-scale dataset for scene understanding, object detection, and image synthesis.

The dataset used in the paper for generating photorealistic images with a bokeh style.

The dataset used in this paper is a diffusion model dataset, specifically Latent Diffusion Models (LDM) and Enhanced Multiscale Image Diffusion (EMU) models.

Cross-view image synthesis aims to translate images between two distinct views, such as synthesizing ground images from aerial images, and vice versa.

The dataset used in the paper is a large set of real images extracted from various object categories of the ImageNet, COCO, and Unpaired real dataset.

The dataset used in the paper is a large set of real images extracted from various object categories of the LSUN dataset and 362K images generated by 20 ProGAN models.

A two-stage cytopathological image synthesis framework for augmenting cervical abnormality screening.

The dataset used in the paper is the LLFF dataset, which contains real-world scenes and is used for training and testing the proposed neural radiance field model.

The NeRF Synthetic dataset is a synthetic dataset created for testing the performance of neural radiance fields.

The OCT2Confocal dataset is the first to include in-vivo grayscale OCT and corresponding ex-vivo colored confocal images.

Diffusion models have recently exhibited remarkable abilities to synthesize striking image samples since the introduction of denoising diffusion probabilistic models (DDPMs).

Fine-grained sketch-based image retrieval (FG-SBIR) aims to minimize the distance between sketches and corresponding images in the embedding space.

The Place2 dataset used in the paper for image synthesis.

A dataset of painted objects and an evaluation protocol to benchmark Collaborative Neural Painting.

The hierarchical keypoint-box layout dataset consists of 3 sets of instruction-answer pairs for instruction tuning of each LLMs.

WebPhoto dataset for image restoration

The dataset is created by augmenting a single input image with masks that indicate the presence of target concepts. The masks can be provided by the user or generated...

A new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes.

LSUN-Bedroom dataset is a large-scale dataset of images of bedrooms.