Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 1,468편

Flickr-Faces-HQ

FFHQ
FFHQ 설명 보기

Flickr-Faces-HQ (FFHQ) consists of 70,000 high-quality PNG images at 1024×1024 resolution and contains considerable variation in terms of age, ethnicity and image background. It also has good coverage of accessories such as eyeglasses, sunglasses, hats, etc. The images were crawled from Flickr, thus inheriting all the biases of that website, and automatically aligned and cropped using dlib. Only images under permissive licenses were collected. Various automatic filters were used to prune the set, and finally Amazon Mechanical Turk was used to remove the occasional statues, paintings, or photos of photos. Source: Flickr-Faces-HQ Dataset (FFHQ) Image Source: https://github.com/NVlabs/ffhq-dataset

관련 논문 6편

FFHQ-Aging

FFHQ-Aging 설명 보기

FFHQ-Aging is a Dataset of human faces designed for benchmarking age transformation algorithms as well as many other possible vision tasks. This dataset is an extention of the NVIDIA FFHQ dataset, on top of the 70,000 original FFHQ images, it also contains the following information for each image: * Gender information (male/female with confidence score) * Age group information (10 classes with confidence score) * Head pose (pitch, roll & yaw) * Glasses type (none, normal or dark) * Eye occlusion score (0-100, different score for each eye) * Full semantic map (19 classes, based on CelebAMask-HQ labels) Source: https://github.com/royorel/FFHQ-Aging-Dataset Image Source: https://github.com/royorel/FFHQ-Aging-Dataset

관련 논문 5편

FFHQ-UV

FFHQ-UV 설명 보기

FFHQ-UV is a large-scale facial UV-texture dataset that contains over 50,000 high-quality texture UV-maps with even illuminations, neutral expressions, and cleaned facial regions, which are desired characteristics for rendering realistic 3D face models under different lighting conditions. The dataset is derived from FFHQ and preserves the most variations in FFHQ. Source: FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction Image Source: https://arxiv.org/pdf/2211.13874v1.pdf

관련 논문 3편

FFHQ-Text

FFHQ-Text 설명 보기

FFHQ-Text is a small-scale face image dataset with large-scale facial attributes, designed for text-to-face generation & manipulation, text-guided facial image manipulation, and other vision-related tasks. This dataset is an extension of the NVIDIA Flickr-Faces-HQ Dataset (FFHQ), which is the selected top 760 female FFHQ images that only contain one complete human face.

관련 논문 1편

Flickr-Faces-HQ-Harmonization

FFHQH
FFHQH 설명 보기

A new dataset for portrait harmonization based on the FFHQ. It contains real images, foreground masks, and synthesized composites. Generating composite images has two steps: alpha mask generation and color augmentation. StyleMatte - portrait matting network was used for mask generation. Color augmentations: brightness, contrast, hue, sharpness adjustment. FFHQH includes 60,000 triplets for train, 5000 for validation and 5000 for test. Triplet stands for <real image, mask, composite image>.

관련 논문 1편

Selection from FFHQ & StyleGAN2:FFHQ (used in "Testing Human Ability To Detect Deepfake Images of Human Faces" study)

Selection from FFHQ & StyleGAN2:FFHQ (used in "Testing Human Ability To Detect Deepfake Images of Human Faces" study) 설명 보기

This dataset is the image stimulus pool of 50 deepfake and 50 real images, used for the experiment in the study titled "Testing Human Ability To Detect Deepfake Images of Human Faces". Images were obtained through random selection from the Flickr Faces High Quality dataset (https://paperswithcode.com/dataset/ffhq) and likewise from output of the StyleGAN2 algorithm (https://paperswithcode.com/method/stylegan2) as trained on the FFHQ dataset. Also included are the 20 deepfake images, similarly obtained (from StyleGAN2:FFHQ), which were used in the familiarization intervention in the study; and the 20 deepfake images (different images but similarly obtained, albeit with an element of curation to select for images with the specific "tell-tale signs" / "visible rendering artefacts") which were used in the advice intervention in the study. The 50 real and 50 deepfake images that were used as test stimuli in the experiment are in /real and /fake respectively; the 20 familiarization images are in /familiarization; and the 20 images used in the advice intervention are in /advice.