Yet Another Computer Vision Index To Datasets (YACVID) - Details

Stand: 2020-06-03 000000m 11:10:24 - Overview

Attribute Current Content New
Name (Institute + Shorttitle)GPA:geometric pose affordance dataset 
Description (include details on usage, files and paper references)Dataset of real 3D people interacting with real 3D scenes. 300k static RGB frames of 13 subject in 8 scenes with ground-truth scene meshes, and motion capture script focus on the interaction between subject and scene geometry, human dynamics, and mimic of human action with scene geometry around.

Diversity and Size
0.3 million 3D human poses and corresponding images, and corresponding scenes representations

13 various size actors

8 scenarios

Accurate Capture and Synchronization
High-resolution 30Hz video from 5 calibrated cameras

Accurate 3D joint positions and joint angles from high-speed motion capture system

Time-of-flight range data

Accurate background subtraction, person bounding boxes

URL Link 
Files (#)300000 
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)3d human pose estimation, human scene interaction, affordance, scene understanding 
Last Changed2020-06-03 
Turing (2.12+3.25=?) :-)