Scanline Resolution-invariant Depth Completion using a Single Image and Sparse LiDAR Point Cloud

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 47
  • Download : 0
Most existing deep learning-based depth completion methods are only suitable for high (e.g. 64-scanline) resolution LiDAR measurements, and they usually fail to predict a reliable dense depth map with low resolution (4, 8, or 16-scanline) LiDAR. However, it is of great interest to reduce the number of LiDAR channels in many aspects (cost, weight of a device, power consumption). In this letter, we propose a new depth completion framework with various LiDAR scanline resolutions, which performs as well as methods built for 64-scanline resolution LiDAR inputs. For this, we define a consistency loss between the predictions from LiDAR measurements of different scanline resolutions. (i.e., 4, 8, 16, 32-scanline LiDAR measurements) Also, we design a fusion module to integrate features from different modalities. Experiments show our proposed method outperforms the current state-of-the-art depth completion methods for input LiDAR measurements of low scanline resolution and performs comparably to the methods(models) for input LiDAR measurements of 64-scanline resolution on the KITTI benchmark dataset.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2021-10
Language
English
Article Type
Article
Citation

IEEE ROBOTICS AND AUTOMATION LETTERS, v.6, no.4, pp.6961 - 6968

ISSN
2377-3766
DOI
10.1109/LRA.2021.3096499
URI
http://hdl.handle.net/10203/287112
Appears in Collection
ME-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0