19 datasets found

Face recognition is a popular form of biometric authentication and due to its widespread use, attacks have become more common as well. Recent studies show that Face Recognition...

The paper presents a dataset called FERET, which consists of a training set FA with a single face image for each of 1196 subjects, and 4 probe sets with pose, expression,...

SFHQ dataset contains synthetic faces

StyleCLIP-FEU uses FlickrFaces-HQ (FFHQ) as the image corpus I.

The dataset used for training and testing the proposed method for restoring a single face image distorted by atmospheric turbulence.

FairFace is a dataset of face images for fairness audit and evaluation, intentionally constructed to be approximately racially balanced.

The LFW-a face database contains 13233 images with varying lighting conditions.

The Extended YaleB database consists of 2,414 frontal face images of 38 subjects under various lighting conditions.

The AR face database contains 100 classes of faces with 26 face images per class with various natural variation and occlusions.

The ORL face database includes 40 classes with 10 images per class with occlusions, scale variations and rotations.

The dataset used for facial attribute prediction and semantic segmentation.

The dataset used in the paper is a set of face images and cat images.

The DISFA dataset is a publicly available spontaneous facial expression dataset which contains 27 subjects (12 females, and 15 males) aged in between [18, 50] and ethnically 3...

BP4D is a large-scale spontaneous facial expression database containing 41 subjects with 23 women and 18 men, each of whom is associated with 8 video-recorded tasks.

The dataset used for the sketch-to-image synthesis task in the paper.

The dataset used for the experiments in the paper, including CelebA-HQ, FFHQ, and AFHQ datasets.

The FRGC-V2 face database is a large-scale face database containing 1000 subjects with 200 images each.

Face recognition and person re-identification using paired image-attribute data, where the attributes (i.e., soft biometrics) are only available during the training phase.

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...