[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

NVlabs/metfaces-dataset

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MetFaces Dataset

Teaser image

MetFaces is an image dataset of human faces extracted from works of art, originally created as part of our work on:

Training Generative Adversarial Networks with Limited Data
Tero Karras (NVIDIA), Miika Aittala (NVIDIA), Janne Hellsten (NVIDIA), Samuli Laine (NVIDIA), Jaakko Lehtinen (NVIDIA and Aalto University), Timo Aila (NVIDIA)
https://arxiv.org/abs/2006.06676

The dataset consists of 1336 high-quality PNG images at 1024×1024 resolution. The images were downloaded via the Metropolitan Museum of Art Collection API, and automatically aligned and cropped using dlib. Various automatic filters were used to prune the set.

For business inquiries, please contact researchinquiries@nvidia.com

For press and other inquiries, please contact Hector Marinez at hmarinez@nvidia.com

Licenses

The source images are made available under the Creative Commons Zero (CC0) license by the Metropolitan Museum of Art. Please read here for more information about their Open Access policy.

The dataset itself (including JSON metadata, processed images, and documentation) is made available under Creative Commons BY-NC 2.0 license by NVIDIA Corporation. You can use, redistribute, and adapt it for non-commercial purposes, as long as you (a) give appropriate credit by citing our paper, and (b) indicate any changes that you've made.

Overview

All data is hosted on Google Drive:

Path Size Files Format Description
metfaces-dataset 14.5 GB 2621 Main folder
├ metfaces.json 1.8 MB 1 JSON Image metadata including original download URL.
├ images 1.6 GB 1336 PNG Aligned and cropped images at 1024×1024
└ unprocessed 13 GB 1284 PNG Original images

Reproducing the dataset

MetFaces 1024x1024 images can be reproduced with the metfaces.py script as follows:

  1. Download the contents of the metfaces-dataset Google Drive folder. Retain the original folder structure (e.g., you should have local/path/metfaces.json, local/path/unprocessed.)
  2. Run metfaces.py --json data/metfaces-dataset.json --source-images data --output-dir out

To reproduce the MetFaces-U dataset ("unaligned MetFaces"), use the following command:

python metfaces.py --json data/metfaces-dataset.json --source-images data \
    --random-shift=0.2 --retry-crops --no-rotation \
    --output-dir out-unaligned

Metadata

The metfaces.json file contains the following information for each image:

[
  {
    "obj_id": "11713",                                  # Metmuseum object ID
    "meta_url": "https://collectionapi.metmuseum.org/public/collection/v1/objects/11713",
    "source_url": "https://images.metmuseum.org/CRDImages/ad/original/ap26.129.1.jpg",
    "source_path": "unprocessed/image-11713.png",       # Original raw image file under local dataset copy
    "source_md5": "c1e4c5a42de6a4d6909d3820c16f9eb5",   # MD5 checksum of the raw image file
    "image_path": "images/11713-00.png",                # Processed 1024x1024 image
    "image_md5": "605a90ab744bdbc9737da5620f2777ab",    # MD5 checksum of the processed image
    "title": "Portrait of a Gentleman",                 # Metmuseum object's title
    "artist_display_name": "Charles Willson Peale",     # Metmuseum object's artist's display name
    "face_spec": {                                      # Info about the raw image:
      "rect": [404, 238, 775, 610],                     # - Axis-aligned rectangle of the face region
      "landmarks": [...],                               # - 68 face landmarks reported by dlib
      "shrink": 2
    },
    "face_idx": 0
  },
  ...
]

For full Metmuseum metadata, you can access the meta_url contents by e.g., curl https://collectionapi.metmuseum.org/public/collection/v1/objects/11713.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages