DDFF12Scene

DDFF 12-Scene dataset consists of in total 720

  • 4D lightfield images: each of which has 9 × 9 undistorted subapertures (383x552). Images are saved as a numpy array and can be loaded with
    import numpy as np
    lf = np.load('LF_0001.npy')
  • registered depth maps: recorded in meters and scaled by a factor of 1000. Depth images are saved as unsigned int 16 bits and only available for "train" set.
    import cv2
    from PIL import Image
    # in meters
    depth = cv2.imread('DEPTH_0001.png', cv2.IMREAD_ANYDEPTH) * 0.001
    depth = np.array(Image.open('DEPTH_0001.png'), dtype=np.float) * 0.001
  • raw images consist of Lytro ILLUM RAW formatted images.
  • calibration files required by Lytro Desktop or Lytro Power Tools.

License

All data in the DDFF 12-Scene benchmark is licensed under a Creative Commons 4.0 Attribution License (CC BY 4.0).

Log

[15-09-2017] – Lightfield images along with registered depth maps and raw Lytro ILLUM images are online.

Bibtex

@inproceedings{hazirbas17ddff,
  title     = {Deep Depth From Focus},
  author    = {C. Hazirbas and L. Leal-Taixé and D. Cremers},
  booktitle = {Arxiv preprint arXiv:1704.01085},
  month     = {April},
  year      = {2017},
}

Share on

Share: Twitter Facebook Google+ LinkedIn