Preprint Article Version 1 This version is not peer-reviewed

CuFusion: Accurate Real‐time Camera Tracking and Volumetric Scene Reconstruction with a Cuboid

Version 1 : Received: 6 August 2017 / Approved: 7 August 2017 / Online: 7 August 2017 (11:03:23 CEST)

How to cite: Zhang, C.; Hu, Y. CuFusion: Accurate Real‐time Camera Tracking and Volumetric Scene Reconstruction with a Cuboid. Preprints 2017, 2017080022 (doi: 10.20944/preprints201708.0022.v1). Zhang, C.; Hu, Y. CuFusion: Accurate Real‐time Camera Tracking and Volumetric Scene Reconstruction with a Cuboid. Preprints 2017, 2017080022 (doi: 10.20944/preprints201708.0022.v1).

Abstract

Given a stream of depth images with a known cuboid reference object present in the scene, we propose a novel approach for accurate camera tracking and volumetric surface reconstruction in real-time. Our contribution in this paper is threefold: (a) utilizing a priori knowledge of the cuboid reference object, we keep drift-free camera tracking without explicit global optimization; (b) we improve the fineness of the volumetric surface representation by proposing a prediction-corrected data fusion strategy rather than simple moving average, which enables accurate reconstruction of high-frequency details such as sharp edges of objects and geometries of high curvature; (c) we introduce a benchmark dataset CU3D containing both synthetic and real-world scanning sequences with ground-truth camera trajectories and surface models for quantitative evaluation of 3D reconstruction algorithms. We test our algorithm on our dataset and demonstrate its accuracy compared with other state-of-the-art algorithms. We release both our dataset and code as opensource1 for other researchers to reproduce and verify our results.

Subject Areas

real‐time reconstruction; SLAM; kinect sensors; depth cameras; open source

Readers' Comments and Ratings (3)

Comment 1
Received: 15 August 2017
Commenter: Bassam Arrfou
The commenter has declared there is no conflict of interests.
Comment: Very interesting work. Could you please provide a link for the CU3D dataset and the code?
+ Respond to this comment
Response 1 to Comment 1
Received: 17 August 2017
Commenter: Chen ZHANG
The commenter has declared there is no conflict of interests.
Comment: Sorry for that incompleteness... I've added the links as footnote 1 in the text. However some error happened when we preprint the manuscript online. I'm now contacting the editors of preprints.org and submitting a follow-up version to fix this issue.
Thank you so much for reminding us of such a carelessness!!!
Response 2 to Comment 1
Received: 17 August 2017
Commenter: Chen ZHANG
The commenter has declared there is no conflict of interests.
Comment: For quick access of the code and data before our re-submission getting online, please checkout this code repo, and see the instructions in README.MD:
https://github.com/zhangxaochen/CuFusion
Leave a public comment
Send a private comment to the author(s)
Rate this article
Views 0
Downloads 0
Comments 3
Metrics 0
Leave a public comment

×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.