-
FlyingThings3D dataset
The FlyingThings3D dataset is a benchmark for stereo matching, consisting of a large collection of images and corresponding disparity maps. -
KeystoneDepth
KeystoneDepth is a collection of over 10,000 rectified antique stereographs of historical scenes captured between 1860 and 1963. -
KITTI 2012
KITTI 2012 is a real-world dataset in the outdoor scenario, and contains 194 training and 195 testing stereo image pairs with the size of 376 × 1240. -
KITTI 2015
The KITTI 2015 dataset is a real-world dataset of street views, containing 200 training stereo image pairs with sparsely labeled disparity from LiDAR data. -
Scene Flow
Stereo matching aims to recover the dense reconstruction of unknown scenes by computing the disparity from rectified stereo images, helping robots intelligently interact with...