Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Maps release_ajd62exzr5ef7erhedvzb4ulja

by Nícolas Rosa, Vitor Guizilini, Valdir Grassi Jr

Released as a article .

2019  

Abstract

This paper addresses the problem of single image depth estimation (SIDE), focusing on improving the quality of deep neural network predictions. In a supervised learning scenario, the quality of predictions is intrinsically related to the training labels, which guide the optimization process. For indoor scenes, structured-light-based depth sensors (e.g. Kinect) are able to provide dense, albeit short-range, depth maps. On the other hand, for outdoor scenes, LiDARs are considered the standard sensor, which comparatively provides much sparser measurements, especially in areas further away. Rather than modifying the neural network architecture to deal with sparse depth maps, this article introduces a novel densification method for depth maps, using the Hilbert Maps framework. A continuous occupancy map is produced based on 3D points from LiDAR scans, and the resulting reconstructed surface is projected into a 2D depth map with arbitrary resolution. Experiments conducted with various subsets of the KITTI dataset show a significant improvement produced by the proposed Sparse-to-Continuous technique, without the introduction of extra information into the training stage.
In text/plain format

Archived Files and Locations

application/pdf  2.4 MB
file_el4uwzf6ivcmtpszhos2ldpnxu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-10-21
Version   v3
Language   en ?
arXiv  1809.09061v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 6f43ea7c-a69f-47ea-aab2-043ec7c5b48e
API URL: JSON