Yet Another Computer Vision Index To Datasets (YACVID) - Details

Stand: 2017-10-22 000000m 22:55:04 - Overview

ok393
Attribute Current Content New
Name (Institute + Shorttitle)4D Light Field Dataset (HCI Heidelberg & CVIA Konstanz) 
Description (include details on usage, files and paper references)A synthetic light field dataset with 24 scenes.

Data provided for each scene:
- 9x9x512x512x3 light fields as individual PNGs
- config files with camera settings and disparity ranges
- per center view (except for the 4 test scenes):
- 512x512 and 5120x5120 depth and disparity maps as PFMs
- 512x512 and 5120x5120 evaluation masks as PNGs

Publication:
Katrin Honauer, Ole Johannsen, Daniel Kondermann, Bastian Goldluecke
"A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields"
In Asian Conference on Computer Vision (ACCV), 2016  
URL Linkhttp://lightfield-analysis.net/ 
Files (#)24 
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)light field, ground truth, synthetic, disparity, depth 
Last Changed2017-10-22 
Turing (2.12+3.25=?) :-)