10 datasets found

The TSS dataset is a benchmark dataset for object recognition. It consists of 400 image pairs from 3 object categories.

The dataset used in the paper for image matching, consisting of 7 datasets with varied image domains, including scene-level, object-centric and aerial images.

Boreas: A multi-season autonomous driving dataset.

ORB: An efficient alternative to SIFT or SURF.

The GL3D dataset is a large-scale dataset for 3D reconstruction from images. It contains 181,280 high-resolution images in 1073 different scenes, along with the image matches,...

The dataset used for training the D2-Net model, consisting of 327,036 image pairs with at least 50% overlap in the sparse SfM point cloud.

The HPatches dataset is a benchmark dataset for local feature matching. It contains 108 sequences of 6 images each, with 52 sequences having illumination changes and 56...

The proposed method, dubbed Dynamic Hyperpixel Flow, learns to compose hypercolumn features on the fly by selecting a small number of relevant layers from a deep convolutional...

The HPatches dataset evaluates the mAP in three different tasks: patch verification, image matching and patch retrieval.

The proposed method, dubbed Dynamic Hyperpixel Flow, learns to compose hypercolumn features on the fly by selecting a small number of relevant layers from a deep convolutional...