preprints.org > 201812.0165.v2

Working Paper Article Version 2 This version is not peer-reviewed

Version 1 : Received: 12 December 2018 / Approved: 13 December 2018 / Online: 13 December 2018 (09:41:36 CET)
Version 2 : Received: 8 April 2019 / Approved: 9 April 2019 / Online: 9 April 2019 (12:24:34 CEST)

3D object reconstruction from depth image streams using Kinect-style depth cameras has been extensively studied. In this paper, we propose an approach for accurate camera tracking and volumetric dense surface reconstruction assuming a known cuboid reference object is present in the scene. Our contribu¬tion is three-fold. (a) We maintain drift-free camera pose tracking by incorporating the 3D geometric constraints of the cuboid reference object into the image registration process. (b) We reformulate the problem of depth stream fusion as a binary classification problem, enabling high-fidelity surface reconstruction, especially in the con¬cave zones of objects. (c) We further present a surface denoising strategy to mitigate the topological inconsistency (e.g., holes and dangling triangles), which facilitates the generation of a noise-free triangle mesh. We extend our public dataset CU3D with several new image sequences, test our algorithm on these sequences and quantitatively compare them with other state-of-the-art algorithms. Both our dataset and our algorithm are available as open-source content at https://github.com/zhangxaochen/CuFusion for oth-er researchers to reproduce and verify our results.

3D object reconstruction, depth cameras, Kinect sensors; open source, signal denoising, SLAM