Aroudj, Samir ; Seemann, Patrick ; Langguth, Fabian ; Guthe, Stefan ; Goesele, Michael (2017)
Visibility-Consistent Thin Surface Reconstruction Using Multi-Scale Kernels.
In: ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), 36 (6)
doi: 10.1145/3130800.3130851
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
One of the key properties of many surface reconstruction techniques is that they represent the volume in front of and behind the surface, e.g., using a variant of signed distance functions. This creates significant problems when reconstructing thin areas of an object since the backside interferes with the reconstruction of the front. We present a two-step technique that avoids this interference and thus imposes no constraints on object thickness. Our method first extracts an approximate surface crust and then iteratively refines the crust to yield the final surface mesh. To extract the crust, we use a novel observation-dependent kernel density estimation to robustly estimate the approximate surface location from the samples. Free space is similarly estimated from the samples' visibility information. In the following refinement, we determine the remaining error using a surface-based kernel interpolation that limits the samples' influence to nearby surface regions with similar orientation and iteratively move the surface towards its true location. We demonstrate our results on synthetic as well as real datasets reconstructed using multi-view stereo techniques or consumer depth sensors.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2017 |
| Autor(en): | Aroudj, Samir ; Seemann, Patrick ; Langguth, Fabian ; Guthe, Stefan ; Goesele, Michael |
| Art des Eintrags: | Bibliographie |
| Titel: | Visibility-Consistent Thin Surface Reconstruction Using Multi-Scale Kernels |
| Sprache: | Englisch |
| Publikationsjahr: | 15 September 2017 |
| Verlag: | ACM |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia) |
| Jahrgang/Volume einer Zeitschrift: | 36 |
| (Heft-)Nummer: | 6 |
| DOI: | 10.1145/3130800.3130851 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | One of the key properties of many surface reconstruction techniques is that they represent the volume in front of and behind the surface, e.g., using a variant of signed distance functions. This creates significant problems when reconstructing thin areas of an object since the backside interferes with the reconstruction of the front. We present a two-step technique that avoids this interference and thus imposes no constraints on object thickness. Our method first extracts an approximate surface crust and then iteratively refines the crust to yield the final surface mesh. To extract the crust, we use a novel observation-dependent kernel density estimation to robustly estimate the approximate surface location from the samples. Free space is similarly estimated from the samples' visibility information. In the following refinement, we determine the remaining error using a surface-based kernel interpolation that limits the samples' influence to nearby surface regions with similar orientation and iteratively move the surface towards its true location. We demonstrate our results on synthetic as well as real datasets reconstructed using multi-view stereo techniques or consumer depth sensors. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Graphics, Capture and Massively Parallel Computing |
| Hinterlegungsdatum: | 15 Sep 2017 16:48 |
| Letzte Änderung: | 09 Dez 2021 11:45 |
| PPN: | |
| Projekte: | https://www.gcc.tu-darmstadt.de/home/proj/tsr/tsr.en.jsp |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum