RGBD Datasets: Past, Present and Future

TL;DR

This paper reviews the development and impact of RGBD datasets since the Kinect, analyzing their role in advancing computer vision and proposing future research directions including synthetic data and dense scene reconstructions.

Contribution

It provides a comprehensive categorization and evaluation of RGBD datasets, highlighting their influence and suggesting future research avenues in the field.

Findings

RGBD datasets have significantly advanced computer vision tasks.

Current datasets cover diverse categories like semantics, pose estimation, and tracking.

Future directions include synthetic data and dense scene reconstructions.

Abstract

Since the launch of the Microsoft Kinect, scores of RGBD datasets have been released. These have propelled advances in areas from reconstruction to gesture recognition. In this paper we explore the field, reviewing datasets across eight categories: semantics, object pose estimation, camera tracking, scene reconstruction, object tracking, human actions, faces and identification. By extracting relevant information in each category we help researchers to find appropriate data for their needs, and we consider which datasets have succeeded in driving computer vision forward and why. Finally, we examine the future of RGBD datasets. We identify key areas which are currently underexplored, and suggest that future directions may include synthetic data and dense reconstructions of static and dynamic scenes.