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

Stand: 2017-09-23 000000m 14:48:48 - Overview

ok1258
Attribute Current Content New
Name (Institute + Shorttitle)Colosseum and San Marco  
Description (include details on usage, files and paper references)The Colosseum and San Marco are two image datasets for dense multiview stereo reconstructions used for evaluating the visual photo realism.

The datasets are downloaded from flickr, aerial and streetside sources and are combined to create the most dense and realistic 3d reconstructions. They are used in a Visual Turing test to decide their realism.

Colosseum - 140k - 3,267 images in sfm
San Marco - 14k - 2,687 images in sfm


The Visual Turing Test for Scene Reconstruction.
Qi Shan, University of Washington; Riley Adams, UW; Brian Curless, University of Washington; Yasutaka Furukawa, Google Inc.; Steve Seitz, University of Washington.

 
URL Linkhttp://homes.cs.washington.edu/~shanqi/work/proj_rome_g1/ 
Files (#)154000 
References (SKIPPED)
Category (SKIPPED)3D reconstruction, Photo-realism 
Tags (single words, spaced)3d, reconstruction, landmark, urban, sfm, aerial, streetside, flickr 
Last Changed2017-09-23 
Turing (2.12+3.25=?) :-)