A scene representation based on multi-modal 2D and 3D features

Date

2007-12-01

Author

Başeski, Emre
Kraft, Dirk
Pugeault, Nicolas
Wörgötter, Florentin
Kalkan, Sinan
Krüger, Norbert

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

282
views

0
downloads

Visually extracted 2D and 3D information have their own advantages and disadvantages that complement each other. Therefore, it is important to be able to switch between the different dimensions according to the requirements of the problem and use them together to combine the reliability of 2D information with the richness of 3D information. In this article, we use 2D and 3D information in a feature-based vision system and demonstrate their complementary properties on different applications (namely: depth prediction, scene interpretation, grasping from vision and object learning). ©2007 IEEE.

URI

https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=50649089996&origin=inward
https://hdl.handle.net/11511/96644

DOI

https://doi.org/10.1109/iccv.2007.4408836

Conference Name

2007 IEEE 11th International Conference on Computer Vision, ICCV

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

A Gamut-Mapping Framework for Color-Accurate Reproduction of HDR Images SİKUDOVA, Elena; POULİ, Tania; ARTUSİ, Alessandro; Akyüz, Ahmet Oğuz; BANTERLE, Francesco; Mazlumoglu, Zeynep Miray; REİNHARD, Erik (2016-07-01) An integrated gamut- and tone-management framework for color-accurate reproduction of high dynamic range images can prevent hue and luminance shifts while taking gamut boundaries into consideration. The proposed approach is conceptually and computationally simple, parameter-free, and compatible with existing tone-mapping operators.
Supervised mesh segmentation for 3D objects with graph Convolutional neural networks Perek, Emir Kaan; Sahillioğlu, Yusuf; Department of Computer Engineering (2019) Mesh segmentation is a fundamental application that is primarily used for understanding and analyzing 3D shapes in a broad range of areas in Computer Science. With the increasing trend of deep learning, there have been many learning-based solutions to the mesh segmentation problem based on the classification of the individual mesh polygons. In this thesis, we cast mesh segmentation as a supervised graph labeling problem by using Graph Convolutional Neural Networks (GCNN). We treat a mesh object as a graph t...
A data-centric unsupervised 3D mesh segmentation method Tümer Sivri, Talya; Sahillioğlu, Yusuf; Department of Modeling and Simulation (2022-12-02) Modeling, texture mapping, shape compression, simplification, and skeleton extracting are popular and essential topics in mesh segmentation applications. As it serves various purposes in computer science, the mesh segmentation problem is an active and prominent research area. With the help of growing machine learning, deep learning algorithms, and computation power, different methods have been applied to solve the 3D mesh segmentation problem more efficiently. In this thesis, we solve the 3D mesh segmentati...
Improving edge detection using ıntersection consistency Çiftçi, Serdar; Yarman Vural, Fatoş Tunay; Kalkan, Sinan; Department of Computer Engineering (2011) Edge detection is an important step in computer vision since edges are utilized by the successor visual processing stages including many tasks such as motion estimation, stereopsis, shape representation and matching, etc. In this study, we test whether a local consistency measure based on image orientation (which we call Intersection Consistency - IC), which was previously shown to improve detection of junctions, can be used for improving the quality of edge detection of seven different detectors; namely, C...
Efficient calibration of a multi-camera measurement system using a target with known dynamics Aykın, Murat Deniz; Saranlı, Afşar; Department of Electrical and Electronics Engineering (2008) Multi camera measurement systems are widely used to extract information about the 3D configuration or “state” of one or more real world objects. Camera calibration is the process of pre-determining all the remaining optical and geometric parameters of the measurement system which are either static or slowly varying. For a single camera, this consist of the internal parameters of the camera device optics and construction while for a multiple camera system, it also includes the geometric positioning of the in...

Citation Formats

E. Başeski, D. Kraft, N. Pugeault, F. Wörgötter, S. Kalkan, and N. Krüger, “A scene representation based on multi-modal 2D and 3D features,” presented at the 2007 IEEE 11th International Conference on Computer Vision, ICCV, Rio de Janeiro, Brezilya, 2007, Accessed: 00, 2022. [Online]. Available: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=50649089996&origin=inward.