InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset

File Description SizeFormat 
BMVC_RGBDI.pdfPublished version6.34 MBAdobe PDFView/Open
Title: InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset
Authors: Li, W
Saeedi Gharahbolagh, S
McCormac, J
Clark, R
Tzoumanikas, D
Ye, Q
Tang, R
Leutenegger, S
Item Type: Conference Paper
Abstract: Datasets have gained an enormous amount of popularity in the computer vision com- munity, from training and evaluation of Deep Learning-based methods to benchmarking Simultaneous Localization and Mapping (SLAM). Without a doubt, synthetic imagery bears a vast potential due to scalability in terms of amounts of data obtainable without tedious manual ground truth annotations or measurements. Here, we present a dataset with the aim of providing a higher degree of photo-realism, larger scale, more variabil- ity as well as serving a wider range of purposes compared to existing datasets. Our dataset leverages the availability of millions of professional interior designs and millions of production-level furniture and object assets – all coming with fine geometric details and high-resolution texture. We render high-resolution and high frame-rate video se- quences following realistic trajectories while supporting various camera types as well as providing inertial measurements. Together with the release of the dataset, we will make executable program of our interactive simulator software as well as our renderer avail- able at https://interiornetdataset.github.io . To showcase the usability and uniqueness of our dataset, we show benchmarking results of both sparse and dense SLAM algorithms.
Issue Date: 3-Sep-2018
Date of Acceptance: 2-Jul-2018
URI: http://hdl.handle.net/10044/1/64285
Publisher: BMVC
Journal / Book Title: Proceedings of the British Machine Vision Conference (BMVC)
Copyright Statement: © 2018. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
Sponsor/Funder: Engineering & Physical Science Research Council (E
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: PO: ERZ1820653
EP/N018494/1
Conference Name: British Machine Vision Conference (BMVC)
Publication Status: Published
Start Date: 2018-09-03
Finish Date: 2018-09-06
Conference Place: Newcastle, UK
Appears in Collections:Faculty of Engineering
Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons