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

Stand: 2017-07-27 000000m 16:49:00 - Overview

ok93
Attribute Current Content New
Name (Institute + Shorttitle)SceneNet RGB-D Synthetic Indoor 
Description (include details on usage, files and paper references)SceneNet RGB-D is dataset comprised of 5 million Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth. It expands the previous work of SceneNet to enable large scale photorealistic rendering of indoor scene trajectories. It provides pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection, and also for geometric computer vision problems such as optical flow, depth estimation, camera pose estimation, and 3D reconstruction. Random sampling permits virtually unlimited scene configurations, and here we provide a set of 5M rendered RGB-D images from over 15K trajectories in synthetic layouts with random but physically simulated object poses. Each layout also has random lighting, camera trajectories, and textures. The scale of this dataset is well suited for pre-training data-driven computer vision techniques from scratch with RGB-D inputs, which previously has been limited by relatively small labelled datasets in NYUv2 and SUN RGB-D. It also provides a basis for investigating 3D scene labelling tasks by providing perfect camera poses and depth data as proxy for a SLAM system.

 
URL Linkhttps://robotvault.bitbucket.io/scenenet-rgbd.html 
Files (#)5000000 
References (SKIPPED)
Category (SKIPPED) 
Tags (single words, spaced)scene indoor synthetic robot navigation rendering 3d reconstruction trajectory lighting segmentation slam 
Last Changed2017-07-27 
Turing (2.12+3.25=?) :-)