DDD: Deep indoor panoramic Depth estimation with Density maps consistency

Simple item page
dc.contributor.authorPintore, Giovannien_US
dc.contributor.authorAgus, Marcoen_US
dc.contributor.authorSignoroni, Albertoen_US
dc.contributor.authorGobbetti, Enricoen_US
dc.contributor.editorCaputo, Arielen_US
dc.contributor.editorGarro, Valeriaen_US
dc.contributor.editorGiachetti, Andreaen_US
dc.contributor.editorCastellani, Umbertoen_US
dc.contributor.editorDulecha, Tinsae Gebrechristosen_US
dc.date.accessioned2024-11-11T12:48:07Z
dc.date.available2024-11-11T12:48:07Z
dc.date.issued2024
dc.description.abstractWe introduce a novel deep neural network for rapid and structurally consistent monocular 360◦ depth estimation in indoor environments. The network infers a depth map from a single gravity-aligned or gravity-rectified equirectangular image of the environment, ensuring that the predicted depth aligns with the typical depth distribution and features of cluttered interior spaces, which are usually enclosed by walls, ceilings, and floors. By leveraging the distinct characteristics of vertical and horizontal features in man-made indoor environments, we introduce a lean network architecture that employs gravity-aligned feature flattening and specialized vision transformers that utilize the input's omnidirectional nature, without segmentation into patches and positional encoding. To enhance the structural consistency of the predicted depth, we introduce a new loss function that evaluates the consistency of density maps by projecting points derived from the inferred depth map onto horizontal and vertical planes. This lightweight architecture has very small computational demands, provides greater structural consistency than competing methods, and does not require the explicit imposition of strong structural priors.en_US
dc.description.sectionheadersComputer Vision
dc.description.seriesinformationSmart Tools and Applications in Graphics - Eurographics Italian Chapter Conference
dc.identifier.doi10.2312/stag.20241336
dc.identifier.isbn978-3-03868-265-3
dc.identifier.issn2617-4855
dc.identifier.pages10 pages
dc.identifier.urihttps://doi.org/10.2312/stag.20241336
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/stag20241336
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Computer vision; Shape inference; Neural networks
dc.subjectComputing methodologies → Computer vision
dc.subjectShape inference
dc.subjectNeural networks
dc.titleDDD: Deep indoor panoramic Depth estimation with Density maps consistencyen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
stag20241336.pdf
Size:
5.74 MB
Format:
Adobe Portable Document Format
Download
Collections
Italian Chapter Conference 2024 - Smart Tools and Apps in Graphics