46 datasets found

The dataset used in the paper is a multi-modal dataset for time-of-flight (ToF) imaging, which includes indoor sequences with challenging light and scene conditions.

A deep learning system to infer the posterior distribution of a dense depth map associated with an image, by exploiting sparse range measurements.

A large-scale dataset of synthetic humans with various actions and poses.

A dataset of 105 individuals with varying poses, head rotations, and occlusions.

A dataset of 118 individuals with a variety of facial expressions and corresponding depth profiles.

The Taskonomy dataset contains 16 types of annotation, including object classification, scene classification, depth estimation, surface normals, curvature estimation, edge...

Depth completion dataset for industrial objects with RGBD images and ground truth depth.

A robust framework for vision-based roadside 3D object detection

The dataset used for depth estimation and object detection.

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.

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...

A dataset for visual odometry, containing 11 sequences with provided ground-truth poses.

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

A dataset for pupil diameter measurement in VR, generated using the Dynamic Periocular Data Generation (DPDG) environment.

A dataset for periocular depth estimation in VR imagery, generated using the Dynamic Periocular Data Generation (DPDG) environment.

The NYUD-v2 dataset is a benchmark for indoor scene segmentation and depth estimation. It contains 1449 images with 4 tasks: semantic segmentation, depth estimation, surface...

Depth-aware Video Panoptic Segmentation (DVPS) is a new challenging vision problem that aims to predict panoptic segmentation and depth in a video simultaneously.

The KITTI odometry dataset is a collection of 22 sequences, containing point clouds, images, and GPS recordings of inner-city traffic, residential areas, highway scenes, and...

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 Virtual KITTI dataset is a synthetic dataset, where the virtual scenes are cloned from the real world KITTI video sequences. Besides the 5 virtual image sequences cloned...