Scene Structure Inference through Scene Map Estimation

Simple item page
dc.contributor.authorHueting, Moosen_US
dc.contributor.authorPatraucean, Vioricaen_US
dc.contributor.authorOvsjanikov, Maksen_US
dc.contributor.authorMitra, Niloy J.en_US
dc.contributor.editorMatthias Hullin and Marc Stamminger and Tino Weinkaufen_US
dc.date.accessioned2016-10-10T08:04:17Z
dc.date.available2016-10-10T08:04:17Z
dc.date.issued2016
dc.description.abstractUnderstanding indoor scene structure from a single RGB image is useful for a wide variety of applications ranging from the editing of scenes to the mining of statistics about space utilization. Most efforts in scene understanding focus on extraction of either dense information such as pixel-level depth or semantic labels, or very sparse information such as bounding boxes obtained through object detection. In this paper we propose the concept of a scene map, a coarse scene representation, which describes the locations of the objects present in the scene from a top-down view (i.e., as they are positioned on the floor), as well as a pipeline to extract such a map from a single RGB image. To this end, we use a synthetic rendering pipeline, which supplies an adapted CNN with virtually unlimited training data. We quantitatively evaluate our results, showing that we clearly outperform a dense baseline approach, and argue that scene maps provide a useful representation for abstract indoor scene understanding.en_US
dc.description.sectionheadersReconstructing and Understanding the World
dc.description.seriesinformationVision, Modeling & Visualization
dc.identifier.doi10.2312/vmv.20161341
dc.identifier.isbn978-3-03868-025-3
dc.identifier.issn-
dc.identifier.pages45-52
dc.identifier.urihttps://doi.org/10.2312/vmv.20161341
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vmv20161341
dc.publisherThe Eurographics Associationen_US
dc.titleScene Structure Inference through Scene Map Estimationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
045-052.pdf
Size:
7.36 MB
Format:
Adobe Portable Document Format
Download
Collections
VMV16