22 datasets found

The ETH3D dataset is a large-scale dataset for multi-view stereo reconstruction. It contains 120 scenes with complex geometric layouts.

The Middlebury and ETH3D datasets are used for stereo matching and 3D reconstruction tasks.

The KITTI 2015 and KITTI 2012 datasets are used for stereo matching and object detection tasks.

ETH3D is a small real-world grayscale dataset with both indoor and outdoor scenes. It contains 27 labeled stereo image pairs for training and 20 stereo pairs for testing.

The dataset used for training and testing the proposed EDNet model for efficient disparity estimation.

SCARED is one of the MICCAI 2019 challenges, and provided a training set acquired from 7 pigs. Each pig corresponds to 5 videos recorded by a binocular camera from 5 different...

The Middlebury 2014 dataset is a benchmark for stereo matching, consisting of 33 pairs of stereo images with sparse depth ground truth.

A benchmark for stereo matching, consisting of 50 stereo pairs with ground truth disparity maps.

A benchmark for stereo matching, consisting of 11 stereo pairs with ground truth disparity maps.

A benchmark for stereo matching, consisting of 75 stereo pairs with ground truth disparity maps.

The FlyingThings3D dataset is a benchmark for stereo matching, consisting of a large collection of images and corresponding disparity maps.

A benchmark for evaluating hand pose tracking/estimation algorithms on passive stereo. Unlike existing benchmarks, it contains both stereo images from a binocular stereo camera...

The Virtual KITTI 2 dataset is a synthetic clone of the real KITTI dataset, containing 5 sequence clones of Scene 01, 02, 06, 18 and 20, and nine variants with diverse weather...

KITTI 2015 dataset contains videos in 200 street scenes captured by RGB cameras, with sparse depth ground truths captured by Velodyne laser scanner.

Relative Depth in Stereo (RDIS) dataset is a dataset containing images labelled with dense relative depths. The ground-truth relative depths are obtained through existing stereo...

Large dataset for stereo matching, optical flow, and scene flow estimation

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.

The Middlebury dataset is a benchmark for stereo vision and 3D reconstruction.

Two publicly available datasets for training and testing: Scene Flow datasets and KITTI2015 dataset

The DTU dataset is a large-scale dataset for multi-view stereo depth inference. It contains over 100 scans taken under 7 different lighting conditions and fixed camera...