Workshop at the European Conference on Computer Vision

ECCV 2014: Computer Vision - ECCV 2014 Workshops pp 238-254

Online 3D Reconstruction and 6-DoF Pose Estimation for RGB-D Sensors

Conference paper

DOI: 10.1007/978-3-319-16178-5_16

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8925)
Cite this paper as:
Lim H., Lim J., Kim H.J. (2015) Online 3D Reconstruction and 6-DoF Pose Estimation for RGB-D Sensors. In: Agapito L., Bronstein M., Rother C. (eds) Computer Vision - ECCV 2014 Workshops. ECCV 2014. Lecture Notes in Computer Science, vol 8925. Springer, Cham


In this paper, we propose an approach to Simultaneous Localization and Mapping (SLAM) for RGB-D sensors. Our system computes 6-DoF pose and sparse feature map of the environment. We propose a novel keyframe selection scheme based on the Fisher information, and new loop closing method that utilizes feature-to-landmark correspondences inspired by image-based localization. As a result, the system effectively mitigates drift that is frequently observed in visual odometry system. Our approach gives lowest relative pose error amongst any other approaches tested on public benchmark dataset. A set of 3D reconstruction results on publicly available RGB-D videos are presented.


Simultaneous Localization and Mapping RGB-D SLAM 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

336125_1_En_16_MOESM1_ESM.mp4 (4 mb)
Supplementary material (MP4 4,068 KB)

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Seoul National UniversitySeoulKorea
  2. 2.Hanyang UniversitySeoulKorea

Personalised recommendations