TU Darmstadt / ULB / TUbiblio

Visibility-Consistent Thin Surface Reconstruction Using Multi-Scale Kernels

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
Article, Bibliographie

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.

Item Type: Article
Erschienen: 2017
Creators: Aroudj, Samir ; Seemann, Patrick ; Langguth, Fabian ; Guthe, Stefan ; Goesele, Michael
Type of entry: Bibliographie
Title: Visibility-Consistent Thin Surface Reconstruction Using Multi-Scale Kernels
Language: English
Date: 15 September 2017
Publisher: ACM
Journal or Publication Title: ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)
Volume of the journal: 36
Issue Number: 6
DOI: 10.1145/3130800.3130851
Corresponding Links:
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.

Divisions: 20 Department of Computer Science
20 Department of Computer Science > Graphics, Capture and Massively Parallel Computing
Date Deposited: 15 Sep 2017 16:48
Last Modified: 09 Dec 2021 11:45
PPN:
Corresponding Links:
Projects: https://www.gcc.tu-darmstadt.de/home/proj/tsr/tsr.en.jsp
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details