82 datasets found

The HKU-IS dataset is used for training the Cycle-IR model.

This dataset contains images of faces with attributes.

This dataset contains images of fashion attributes.

The Kodak PhotoCD image dataset is a collection of images used for testing image compression algorithms.

The Visual Genome Relationship Dataset contains 108,077 images and 1,531,448 relationships.

The Visual Relationship Dataset contains 5000 images with 100 object categories and 70 predicates.

The MegaFace Challenge 1 dataset contains 1 million images of 690K individuals.

The dataset Erpbero contains 2,591 images.

The dataset Aos Hus contains 811 images.

The dataset Dubrovnik6K contains 6,044 images.

The dataset Rome16K contains 16,000 images.

The Open Image Dataset (OID) is a large-scale image dataset that contains a diverse set of images.

The dataset used for training and testing the proposed Cascaded Edge and Image Learning Network (CEILNet) for single image reflection removal and image smoothing.

The yuru-chara image dataset is a collection of images of yuru-charas, which are mascot characters created by local governments and companies for publicizing information on...

A dataset of 50 icons with their 2D contours

A large-scale image dataset of wood surface defects for automated vision-based quality control processes.

The LAION-2B-en dataset contains 100M examples from the LAION-2B-en dataset.

VITON-HD dataset contains 13679 pairs of half-body view and upper in-store clothing in 13 categories

DeepFashion Multimodal dataset contains 12701 full-body images in 24 categories

The dataset used in the paper is a collection of trained networks and their corresponding datasets.