This is not the latest version of this item. The latest version can be found here.
Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image
Name
1709.07492.pdf
Description
Submitted version
Size
2.9 MB
Format
Adobe PDF
Checksum (MD5)
d553cd9e2cf7fa39c18d2dfc876f55a6
Date Issued
May 2018
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
2018. "Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image."
Version
Original manuscript
Abstract
© 2018 IEEE. We consider the problem of dense depth prediction from a sparse set of depth measurements and a single RGB image. Since depth estimation from monocular images alone is inherently ambiguous and unreliable, to attain a higher level of robustness and accuracy, we introduce additional sparse depth samples, which are either acquired with a low-resolution depth sensor or computed via visual Simultaneous Localization and Mapping (SLAM) algorithms. We propose the use of a single deep regression network to learn directly from the RGB-D raw data, and explore the impact of number of depth samples on prediction accuracy. Our experiments show that, compared to using only RGB images, the addition of 100 spatially random depth samples reduces the prediction root-mean-square error by 50% on the NYU-Depth-v2 indoor dataset. It also boosts the percentage of reliable prediction from 59 % to 92 % on the KITTI dataset. We demonstrate two applications of the proposed algorithm: a plug-in module in SLAM to convert sparse maps to dense maps, and super-resolution for LiDARs. Software22https://github.com/fangchangma/sparse-to-dense and video demonstration33https://www.youtube.com/watch?v=vNIIT-M7×7Y are publicly available.
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
10.1109/ICRA.2018.8460184
