MatchBox: Indoor Image Matching via Box-like Scene Estimation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F15%3A00223267" target="_blank" >RIV/68407700:21230/15:00223267 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/3DV.2014.56" target="_blank" >http://dx.doi.org/10.1109/3DV.2014.56</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/3DV.2014.56" target="_blank" >10.1109/3DV.2014.56</a>
Alternative languages
Result language
angličtina
Original language name
MatchBox: Indoor Image Matching via Box-like Scene Estimation
Original language description
Keypoint matching in images of indoor scenes traditionally employs features like SIFT, GIST and HOG. While features work very well for two images related to each other by small camera transformations, we commonly observe a drop in performance for patchesrepresenting scene elements visualized from a very different perspective. Since increasing the space of considered local transformations for feature matching decreases their discriminative abilities, we propose a more global approach inspired by the recent success of monocular scene understanding. In particular we propose to reconstruct a box-like model of the scene from every single image and use it to rectify images before matching. We show that a monocular scene model reconstruction and rectification preceding standard feature matching significantly improves keypoint matching and dramatic ally improves reconstruction of difficult indoor scenes.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
<a href="/en/project/TA02011275" target="_blank" >TA02011275: ATOM - Automatic Three-dimensional Terrain Monitoring</a><br>
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
3DV 2014: International Conference on 3D Vision
ISBN
978-1-4799-7001-8
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
705-712
Publisher name
IEEE Computer Society Press
Place of publication
Los Alamitos
Event location
Tokyo
Event date
Dec 8, 2014
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—