Vision

812 Datasets

Datasets


HandNet annotated hand dataset

The HandNet dataset contains depth images of 10 participants hands non-rigidly deforming infront of a RealSense RGB-D camera. This dataset includes 2...

rgbd, hand, articulation, video, segmentation, classification, pose, fingertip, detection

Shadow Removal Dataset and ...

To encourage the open comparison of single image shadow removal in community, we provide an online benchmark site and a dataset. Our quantitatively veri...

illumination, shadow, benchmark, singleview, removal

SPHERE human skeleton movem...

The SPHERE human skeleton movements dataset was created using a Kinect camera, that measures distances and provides a depth map of the scene instead of ...

motion, skeleton, kinect, movement, depth, human, action, video, behavior

Ian Dworkin (McMaster Unive...

This is the database of biological images (from the genetics model system, Drosophila melanogaster, a fruit fly) across multiple levels of variation. ...

classification, fly, biology, animal, variation, genetic

1DSfM Landmarks

The 1DSfM Landmarks is a collection of community-based image reconstruction by Kyle Wilson and is comprised of 14 datasets with comparison to bundler gr...

urban, 3d, benchmark, city, reconstruction, landmark, groundtruth

CMP map2photo

The CMP map2photo dataset consists of 6 pairs, where one image is satellite photo and second image is a map of the same area. The task is to match thes...

sensing, baseline, matching, description, map, feature, remote, detection, wide

CMP Extreme Zoom Dataset

The Extreme Zoom Dataset. EZD is a 6 image sets with incleasing zoom factor from general scene view to focusing on single detail. MODS: Fast and Robus...

description, detection, zoom, viewpoint, matching, feature

CAMP-TUM: Multiple Human Po...

We introduce the Shelf dataset for multiple human pose estimation from multiple views. In addition we annotate the body joints in the Campus dataset fro...

motion, multiple, 3d, estimation, capture, pose, human, view

"Central" Pedestrian Crossi...

Three pedestrian crossing sequences

tracking

Freiburg-Berkeley Motion Se...

The Freiburg-Berkeley Motion Segmentation Dataset (FBMS-59) is an extension of the BMS dataset with 33 additional video sequences. A total of 720 frames...

motion, benchmark, video, object, pedestrian, segmentation, tracking, groundtruth