3D floor plan recovery from overlapping spherical images
Abstract We present a novel approach to automatically recover, from a small set of partially overlapping spherical images, an indoor structure representation in terms of a 3D floor plan registered with a set of 3D environment maps. We introduce several improvements over previous approaches based on...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2018-11-01
|
| Series: | Computational Visual Media |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1007/s41095-018-0125-9 |
| _version_ | 1818954636577472512 |
|---|---|
| author | Giovanni Pintore Fabio Ganovelli Ruggero Pintus Roberto Scopigno Enrico Gobbetti |
| author_facet | Giovanni Pintore Fabio Ganovelli Ruggero Pintus Roberto Scopigno Enrico Gobbetti |
| author_sort | Giovanni Pintore |
| collection | DOAJ |
| description | Abstract We present a novel approach to automatically recover, from a small set of partially overlapping spherical images, an indoor structure representation in terms of a 3D floor plan registered with a set of 3D environment maps. We introduce several improvements over previous approaches based on color and spatial reasoning exploiting Manhattan world priors. In particular, we introduce a new method for geometric context extraction based on a 3D facet representation, which combines color distribution analysis of individual images with sparse multi-view clues. We also introduce an efficient method to combine the facets from different viewpoints in a single consistent model, taking into the reliability of the facet information. The resulting capture and reconstruction pipeline automatically generates 3D multi-room environments in cases where most previous approaches fail, e.g., in the presence of hidden corners and large clutter, without the need for additional dense 3D data or tools. We demonstrate the effectiveness and performance of our approach on different real-world indoor scenes. Our test data is available to allow further studies and comparisons. |
| first_indexed | 2024-12-20T10:25:19Z |
| format | Article |
| id | doaj.art-d10553866d7442e5b5fc49633a75209a |
| institution | Directory Open Access Journal |
| issn | 2096-0433 2096-0662 |
| language | English |
| last_indexed | 2024-12-20T10:25:19Z |
| publishDate | 2018-11-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Computational Visual Media |
| spelling | doaj.art-d10553866d7442e5b5fc49633a75209a2022-12-21T19:43:51ZengSpringerOpenComputational Visual Media2096-04332096-06622018-11-014436738310.1007/s41095-018-0125-93D floor plan recovery from overlapping spherical imagesGiovanni Pintore0Fabio Ganovelli1Ruggero Pintus2Roberto Scopigno3Enrico Gobbetti4CRS4, Visual Computing GroupCRS4, Visual Computing GroupCRS4, Visual Computing GroupCRS4, Visual Computing GroupCNR-ISTI, Visual Computing GroupAbstract We present a novel approach to automatically recover, from a small set of partially overlapping spherical images, an indoor structure representation in terms of a 3D floor plan registered with a set of 3D environment maps. We introduce several improvements over previous approaches based on color and spatial reasoning exploiting Manhattan world priors. In particular, we introduce a new method for geometric context extraction based on a 3D facet representation, which combines color distribution analysis of individual images with sparse multi-view clues. We also introduce an efficient method to combine the facets from different viewpoints in a single consistent model, taking into the reliability of the facet information. The resulting capture and reconstruction pipeline automatically generates 3D multi-room environments in cases where most previous approaches fail, e.g., in the presence of hidden corners and large clutter, without the need for additional dense 3D data or tools. We demonstrate the effectiveness and performance of our approach on different real-world indoor scenes. Our test data is available to allow further studies and comparisons.http://link.springer.com/article/10.1007/s41095-018-0125-9indoor reconstructionspherical panoramic cameras360 degree photographymulti-room environments |
| spellingShingle | Giovanni Pintore Fabio Ganovelli Ruggero Pintus Roberto Scopigno Enrico Gobbetti 3D floor plan recovery from overlapping spherical images Computational Visual Media indoor reconstruction spherical panoramic cameras 360 degree photography multi-room environments |
| title | 3D floor plan recovery from overlapping spherical images |
| title_full | 3D floor plan recovery from overlapping spherical images |
| title_fullStr | 3D floor plan recovery from overlapping spherical images |
| title_full_unstemmed | 3D floor plan recovery from overlapping spherical images |
| title_short | 3D floor plan recovery from overlapping spherical images |
| title_sort | 3d floor plan recovery from overlapping spherical images |
| topic | indoor reconstruction spherical panoramic cameras 360 degree photography multi-room environments |
| url | http://link.springer.com/article/10.1007/s41095-018-0125-9 |
| work_keys_str_mv | AT giovannipintore 3dfloorplanrecoveryfromoverlappingsphericalimages AT fabioganovelli 3dfloorplanrecoveryfromoverlappingsphericalimages AT ruggeropintus 3dfloorplanrecoveryfromoverlappingsphericalimages AT robertoscopigno 3dfloorplanrecoveryfromoverlappingsphericalimages AT enricogobbetti 3dfloorplanrecoveryfromoverlappingsphericalimages |