Modeling 2D appearance evolution for 3D object categorization

3D object categorization is a non-trivial task in computer vision encompassing many real-world applications. We pose the problem of categorizing 3D polygon meshes as learning appearance evolution from multi-view 2D images. Given a corpus of 3D polygon meshes, we first render the corresponding RGB an...

Full description

Bibliographic Details
Main Authors:	Mohd Zaki, Hasan Firdaus, Shafait, Faisal, Mian, Ajmal
Format:	Conference or Workshop Item
Language:	English English
Published:	IEEE 2016
Subjects:	QA75 Electronic computers. Computer science
Online Access:	http://irep.iium.edu.my/64702/ http://irep.iium.edu.my/64702/ http://irep.iium.edu.my/64702/ http://irep.iium.edu.my/64702/7/64702%20Modeling%202D%20Appearance%20Evolution%20for%203D%20Object%20Categorization.pdf http://irep.iium.edu.my/64702/8/64702%20Modeling%202D%20Appearance%20Evolution%20for%203D%20Object%20Categorization%20_%20scopus.pdf

id	iium-64702
recordtype	eprints
spelling	iium-647022018-08-06T07:35:53Z http://irep.iium.edu.my/64702/ Modeling 2D appearance evolution for 3D object categorization Mohd Zaki, Hasan Firdaus Shafait, Faisal Mian, Ajmal QA75 Electronic computers. Computer science 3D object categorization is a non-trivial task in computer vision encompassing many real-world applications. We pose the problem of categorizing 3D polygon meshes as learning appearance evolution from multi-view 2D images. Given a corpus of 3D polygon meshes, we first render the corresponding RGB and depth images from multiple viewpoints on a uniform sphere. Using rank pooling, we propose two methods to learn the appearance evolution of the 2D views. Firstly, we train view-invariant models based on a deep convolutional neural network (CNN) using the rendered RGB-D images and learn to rank the first fully connected layer activations and, therefore, capture the evolution of these extracted features. The parameters learned during this process are used as the 3D shape representations. In the second method, we learn the aggregation of the views from the outset by employing the ranking machine to the rendered RGB- D images directly, which produces aggregated 2D images which we term as ``3D shape images". We then learn CNN models on this novel shape representation for both RGB and depth which encode salient geometrical structure of the polygon. Experiments on the ModelNet40 and ModelNet10 datasets show that the proposed method consistently outperforms existing state-of-the-art algorithms in 3D shape recognition. IEEE 2016-12-26 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/64702/7/64702%20Modeling%202D%20Appearance%20Evolution%20for%203D%20Object%20Categorization.pdf application/pdf en http://irep.iium.edu.my/64702/8/64702%20Modeling%202D%20Appearance%20Evolution%20for%203D%20Object%20Categorization%20_%20scopus.pdf Mohd Zaki, Hasan Firdaus and Shafait, Faisal and Mian, Ajmal (2016) Modeling 2D appearance evolution for 3D object categorization. In: 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 30th November - 2nd December 2016, Gold Coast, QLD, Australia. https://ieeexplore.ieee.org/document/7797065/ 10.1109/DICTA.2016.7797065
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English English
topic	QA75 Electronic computers. Computer science
spellingShingle	QA75 Electronic computers. Computer science Mohd Zaki, Hasan Firdaus Shafait, Faisal Mian, Ajmal Modeling 2D appearance evolution for 3D object categorization
description	3D object categorization is a non-trivial task in computer vision encompassing many real-world applications. We pose the problem of categorizing 3D polygon meshes as learning appearance evolution from multi-view 2D images. Given a corpus of 3D polygon meshes, we first render the corresponding RGB and depth images from multiple viewpoints on a uniform sphere. Using rank pooling, we propose two methods to learn the appearance evolution of the 2D views. Firstly, we train view-invariant models based on a deep convolutional neural network (CNN) using the rendered RGB-D images and learn to rank the first fully connected layer activations and, therefore, capture the evolution of these extracted features. The parameters learned during this process are used as the 3D shape representations. In the second method, we learn the aggregation of the views from the outset by employing the ranking machine to the rendered RGB- D images directly, which produces aggregated 2D images which we term as ``3D shape images". We then learn CNN models on this novel shape representation for both RGB and depth which encode salient geometrical structure of the polygon. Experiments on the ModelNet40 and ModelNet10 datasets show that the proposed method consistently outperforms existing state-of-the-art algorithms in 3D shape recognition.
format	Conference or Workshop Item
author	Mohd Zaki, Hasan Firdaus Shafait, Faisal Mian, Ajmal
author_facet	Mohd Zaki, Hasan Firdaus Shafait, Faisal Mian, Ajmal
author_sort	Mohd Zaki, Hasan Firdaus
title	Modeling 2D appearance evolution for 3D object categorization
title_short	Modeling 2D appearance evolution for 3D object categorization
title_full	Modeling 2D appearance evolution for 3D object categorization
title_fullStr	Modeling 2D appearance evolution for 3D object categorization
title_full_unstemmed	Modeling 2D appearance evolution for 3D object categorization
title_sort	modeling 2d appearance evolution for 3d object categorization
publisher	IEEE
publishDate	2016
url	http://irep.iium.edu.my/64702/ http://irep.iium.edu.my/64702/ http://irep.iium.edu.my/64702/ http://irep.iium.edu.my/64702/7/64702%20Modeling%202D%20Appearance%20Evolution%20for%203D%20Object%20Categorization.pdf http://irep.iium.edu.my/64702/8/64702%20Modeling%202D%20Appearance%20Evolution%20for%203D%20Object%20Categorization%20_%20scopus.pdf
first_indexed	2023-09-18T21:31:49Z
last_indexed	2023-09-18T21:31:49Z
_version_	1777412561228005376

Modeling 2D appearance evolution for 3D object categorization

Similar Items