Fast and Accurate Refinement Method for 3D Reconstruction from Stereo Spherical Images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F15%3APU116986" target="_blank" >RIV/00216305:26230/15:PU116986 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=10866" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=10866</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0005310805750583" target="_blank" >10.5220/0005310805750583</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Fast and Accurate Refinement Method for 3D Reconstruction from Stereo Spherical Images

Popis výsledku v původním jazyce

Realistic 3D models of the environment are beneficial in many fields, from natural or man-made structure inspection and volumetric analysis, to movie-making, in particular, special effects integration to natural scenes. Spherical cameras are becoming popular in environment modelling because they capture the full surrounding scene visible from the camera location as a consistent seamless image at once. In this paper, we propose a novel pipeline to obtain fast and accurate 3D reconstructions from spherical images. In order to have a better estimation of the structure, the system integrates a joint camera pose and structure refinement step. This strategy proves to be much faster, yet equally accurate, when compared to the conventional method, registration of a dense point cloud via iterative closest point (ICP). Both methods require an initial estimate for successful convergence. The initial positions of the 3D points are obtained from stereo processing of pair of spherical images with known baseline. The initial positions of the cameras are obtained from a robust wide-baseline matching procedure. The performance and accuracy of the 3D reconstruction pipeline is analysed through extensive tests on several indoor and outdoor datasets.

Název v anglickém jazyce

Fast and Accurate Refinement Method for 3D Reconstruction from Stereo Spherical Images

Popis výsledku anglicky

Realistic 3D models of the environment are beneficial in many fields, from natural or man-made structure inspection and volumetric analysis, to movie-making, in particular, special effects integration to natural scenes. Spherical cameras are becoming popular in environment modelling because they capture the full surrounding scene visible from the camera location as a consistent seamless image at once. In this paper, we propose a novel pipeline to obtain fast and accurate 3D reconstructions from spherical images. In order to have a better estimation of the structure, the system integrates a joint camera pose and structure refinement step. This strategy proves to be much faster, yet equally accurate, when compared to the conventional method, registration of a dense point cloud via iterative closest point (ICP). Both methods require an initial estimate for successful convergence. The initial positions of the 3D points are obtained from stereo processing of pair of spherical images with known baseline. The initial positions of the cameras are obtained from a robust wide-baseline matching procedure. The performance and accuracy of the 3D reconstruction pipeline is analysed through extensive tests on several indoor and outdoor datasets.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/7E13044" target="_blank" >7E13044: IMPART - Intelligent Management Platform for Advanced Real-Time media processes</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 10th International Conference on Computer Vision Theory and Applications

ISBN

978-989-8425-47-8

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

1-8

Název nakladatele

Institute of Electrical and Electronics Engineers

Místo vydání

Berlin

Místo konání akce

Berlin, Německo

Datum konání akce

11. 3. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—