High Resolution Surface Reconstruction from Overlapping Multiple-Views
| Autor: | Mariette Yvinec, Nader Salman |
|---|---|
| Přispěvatelé: | Geometric computing (GEOMETRICA), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria), ANR-07-RIAM-0013,GYROVIZ,Modélisation Automatique 3D Temps réel Robuste à partir d'Images Localisées(2007), Gyroviz, ANR-07- AM-013,Gyroviz, ANR-07- AM-013 |
| Jazyk: | angličtina |
| Rok vydání: | 2009 |
| Předmět: |
Multiple-views
Computer science Point cloud ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Cgal Delaunay refinement [INFO.INFO-CG]Computer Science [cs]/Computational Geometry [cs.CG] 0202 electrical engineering electronic engineering information engineering Computer vision ComputingMethodologies_COMPUTERGRAPHICS business.industry Delaunay triangulation Visibility (geometry) Process (computing) ACM: I.: Computing Methodologies/I.3: COMPUTER GRAPHICS/I.3.5: Computational Geometry and Object Modeling Triangle soup Restricted Delaunay triangulation 020202 computer hardware & architecture Stereopsis Data point ACM: I.: Computing Methodologies/I.4: IMAGE PROCESSING AND COMPUTER VISION/I.4.5: Reconstruction Computer Science::Computer Vision and Pattern Recognition CImg 020201 artificial intelligence & image processing Artificial intelligence Noise (video) business Surface reconstruction Ruppert's algorithm |
| Zdroj: | SoCG 2009-Twenty-fifth annual symposium on Computational geometry SoCG 2009-Twenty-fifth annual symposium on Computational geometry, Jun 2009, Aarhus, Netherlands. pp.104-105, ⟨10.1145/1542362.1542386⟩ Symposium on Computational Geometry |
| DOI: | 10.1145/1542362.1542386⟩ |
| Popis: | International audience; Extracting a computer model of a real scene from a sequence of views, is one of the most challenging and fundamental problems in computer vision. Stereo vision algorithms allow us to extract from the images a sparse 3D point cloud on the scene surfaces. However, computing an accurate mesh of the scene based on such poor quality data points (noise, sparsity) is very difficult. Here we describe a simple yet original approach that uses both the stereo vision extracted point cloud and the calibrated images. Our method is a three-stage process in which the first stage merges, filters and smoothes the input 3D points. The second stage builds for each calibrated image a triangular depth-map and fuses the set of depth-maps into a triangle soup that minimize violations of size and visibility constraints. Finally, a mesh is computed from the triangle soup using a reconstruction method that combines restricted Delaunay triangulation and Delaunay refinement. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|