32 datasets found

KeystoneDepth is a collection of over 10,000 rectified antique stereographs of historical scenes captured between 1860 and 1963.

The dataset used in the paper is the TUM-VIE dataset, which contains a stereo visual-inertial event dataset.

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 CARLA dataset is a complex urban-like environment with multi-agent dynamics, pedestrians, intersections, cross-traffic, roundabout, and changing weather conditions.

Natural scenes dataset for stereo depth estimation

The KITTI Vision Benchmark Suite is a dataset used for object detection and tracking in autonomous vehicles.

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

Dense pixel matching is required for many computer vision algorithms such as disparity, optical flow or scene flow estimation. Feature Pyramid Networks (FPN) have proven to be a...

The MVSEC dataset is a dataset for event-based camera data, featuring 5 sequences of a car on the street, as well as 4 short indoor sequences shot from a flying quadrotor.

The dataset is used for learning a multi-view stereo machine.

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.

Stereo matching aims to recover the dense reconstruction of unknown scenes by computing the disparity from rectified stereo images, helping robots intelligently interact with...