Sparse-to-Continuous: Enhancing Monocular Depth Estimation using
Occupancy Maps
release_ajd62exzr5ef7erhedvzb4ulja
by
Nícolas Rosa, Vitor Guizilini, Valdir Grassi Jr
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) |
1809.09061v3
access all versions, variants, and formats of this works (eg, pre-prints)