The CERTH/ITI dataset of Kinect-based 3D scans The CERTH/ITI dataset of Kinect-based 3D scans consists of multi-view range scans of small-sized objects using a turntable. Range scans were captured using a Microsoft Kinect sensor, as well as an accurate laser scanner (Vivid VI-700 Non-contact 3D Digitizer), whose reconstructions can serve as ground-truth data. The construction of this dataset was motivated by the lack of a relevant Kinect dataset, despite the fact that Kinect has attracted the attention of many researchers and home enthusiasts. Thus, the core idea behind the construction of this dataset, is to allow the validation of 3D surface reconstruction methodologies for point sets extracted using Kinect sensors.

The dataset consists of multi-view range scans of 59 objects, along with the necessary calibration information that can be used for experimentation in the field of 3D reconstruction from Kinect depth data. Since the dataset comes in classes of similar objects, it can also be used for classification purposes, using the provided 3D features, along with RGB information provided. For each object, the following information is provided:

•  Depth values per view
•  RGB information (registered with depth information) per view
• 3D information (X,Y,Z) for each view
• Registered point clouds for all views

More on CERTH/ITI Kinect based 3DScans…

Relevant papers

A. Doumanoglou, S. Asteriadis, D. Alexiadis, D. Zarpalas, P. Daras, “A Dataset of Kinect-based 3D scans”, 11th IEEE IVMSP Workshop: 3D Image/Video Technologies and Applications, Yonsei University, Seoul, Korea, 10-12 June 2013