Patch Matching

The HPatches is a recent dataset for local patch descriptor evaluation that consists of 116 sequences of 6 images with known homography. The dataset is split into two parts: viewpoint - 59 sequences with significant viewpoint change and illumination - 57 sequences with significant illumination change, both natural and artificial. Source: RF-Net: An End-to-End Image Matching Network based on Receptive Field Image Source: https://www.robots.ox.ac.uk/~vgg/publications/2017/Balntas17/balntas17.pdf

The Viewpoint Invariant Pedestrian Recognition (VIPeR) dataset includes 632 people and two outdoor cameras under different viewpoints and light conditions. Each person has one image per camera and each image has been scaled to be 128×48 pixels. It provides the pose angle of each person as 0° (front), 45°, 90° (right), 135°, and 180° (back). Source: PaMM: Pose-aware Multi-shot Matching for Improving Person Re-identification Image Source: Qin et al

The ETH SfM (structure-from-motion) dataset is a dataset for 3D Reconstruction. The benchmark investigates how different methods perform in terms of building a 3D model from a set of available 2D images. Source: SOSNet: Second Order Similarity Regularization forLocal Descriptor Learning Image Source: https://cvg.ethz.ch/research/symmetries-in-sfm/

The PhotoSynth (PS) dataset for patch matching consists of a total of 30 scenes with 25 scenes for training and 5 scenes for validation. The different image pairs are captured in different illumination conditions, at different scales and with different viewpoints. Source: https://arxiv.org/abs/1801.01466 Image Source: https://github.com/rmitra/PS-Dataset