Login
Deep Depth From Focus (bibtex)
by C. Hazirbas, S. G. Soyer, M. C. Staab, L. Leal-Taixé and D. Cremers
Reference:
Deep Depth From Focus (C. Hazirbas, S. G. Soyer, M. C. Staab, L. Leal-Taixé and D. Cremers), In Asian Conference on Computer Vision (ACCV), 2018. ([arxiv], Deep Depth From Focus,[dataset])
Bibtex Entry:
@inproceedings{hazirbas18ddff,
author = {C. Hazirbas and S. G. Soyer and M. C. Staab and L. Leal-Taixé and D. Cremers},
title = {{Deep Depth From Focus}},
year = {2018},
month = {December},
booktitle = {Asian Conference on Computer Vision (ACCV)},
keywords = {deep learning},
}
Powered by bibtexbrowser
DDFF 12-Scene
4.5D Lightfield-Depth Benchmark
Depth From Focus Competition on the DDFF 12-Scene Dataset
DDFF 12-Scene dataset consists of 720 lightfield images and coregistered depth maps.
- Lightfield: 4D lightfield images; each of which has 9 × 9 × 383 × 552 undistorted subapertures Images are saved as numpy arrays and can be loaded as follows:
import numpy as np
lf = np.load('LF_0001.npy')
- Lightfield-mat: 4D lightfield images in Matlab format
- Depth: registered depth maps; recorded in meters and scaled by a factor of 1000. Depth images are saved in uint16 bits and only available for "train" and "val" sets:
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
- RawImage: raw images consist of Lytro ILLUM RAW formatted images
- CalibPattern: calibration pattern for the Lytro ILLUM camera
- WhiteImages: white images required by the Lytro Desktop
Depth From Focus Competition
Please submit your test results to the DFF competition.
License
All data in the DDFF 12-Scene benchmark is licensed under a Creative Commons 4.0 Attribution License (CC BY 4.0).
Log
[24-04-2018] – Trainval/Test hdf5 files added [07-12-2017] – Lighfield images in Matlab format [05-12-2017] – Lighfield calibration pattern and white images [15-09-2017] – Lightfield images, registered depth maps and raw Lytro ILLUM images
Bibtex
