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

Stand: 2020-06-05 000000m 07:31:35 - Overview

Attribute Current Content New
Name (Institute + Shorttitle)PhotoTourism Pair Patch 
Description (include details on usage, files and paper references)The data is taken from Photo Tourism reconstructions from Trevi Fountain (Rome), Notre Dame (Paris) and Half Dome (Yosemite). Each dataset consists of a series of corresponding patches, which are obtained by projecting 3D points from Photo Tourism reconstructions back into the original images.

The PhotoTourism Pair dataset consists of 1024 x 1024 bitmap images, each containing a 16 x 16 array of image patches sampled at 64x64 grayscale pixels with a canonical scale and orientation. It is used for retrieval of similar image pair patches (not full images but cropped patches), similar to be pure descriptor comparison evaluation by Mikolajczyk.

S. Winder and M. Brown. Learning Local Image Descriptors. To appear International Conference on Computer Vision and Pattern Recognition (CVPR2007) (see PAMI 2011) 
URL Link 
Files (#)300000 
References (SKIPPED)
Category (SKIPPED)Feature Matching, Feature Description 
Tags (single words, spaced)feature matching description pair sfm patch learning 
Last Changed2020-06-05 
Turing (2.12+3.25=?) :-)