Neural Colorization of Laser Scans

dc.contributor.authorComino Trinidad, Marcen_US
dc.contributor.authorAndujar, Carlosen_US
dc.contributor.authorBosch, Carlesen_US
dc.contributor.authorChica, Antonioen_US
dc.contributor.authorMuñoz-Pandiella, Imanolen_US
dc.contributor.editorOrtega, Lidia M. and Chica, Antonioen_US
dc.date.accessioned2021-09-21T08:08:57Z
dc.date.available2021-09-21T08:08:57Z
dc.date.issued2021
dc.description.abstractLaser scanners enable the digitization of 3D surfaces by generating a point cloud where each point sample includes an intensity (infrared reflectivity) value. Some LiDAR scanners also incorporate cameras to capture the color of the surfaces visible from the scanner location. Getting usable colors everywhere across 360° scans is a challenging task, especially for indoor scenes. LiDAR scanners lack flashes, and placing proper light sources for a 360° indoor scene is either unfeasible or undesirable. As a result, color data from LiDAR scans often do not have an adequate quality, either because of poor exposition (too bright or too dark areas) or because of severe illumination changes between scans (e.g. direct Sunlight vs cloudy lighting). In this paper, we present a new method to recover plausible color data from the infrared data available in LiDAR scans. The main idea is to train an adapted image-to-image translation network using color and intensity values on well-exposed areas of scans. At inference time, the network is able to recover plausible color using exclusively the intensity values. The immediate application of our approach is the selective colorization of LiDAR data in those scans or regions with missing or poor color data.en_US
dc.description.sectionheadersFull Papers - Capture Techniques and Pathfinding
dc.description.seriesinformationSpanish Computer Graphics Conference (CEIG)
dc.identifier.doi10.2312/ceig.20211356
dc.identifier.isbn978-3-03868-160-1
dc.identifier.pages9-14
dc.identifier.urihttps://doi.org/10.2312/ceig.20211356
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/ceig20211356
dc.publisherThe Eurographics Associationen_US
dc.titleNeural Colorization of Laser Scansen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
009-014.pdf
Size:
17.4 MB
Format:
Adobe Portable Document Format
Collections