Deformable Shape Retrieval with Missing Parts

Abstract
Partial similarity problems arise in numerous applications that involve real data acquisition by 3D sensors, inevitably leading to missing parts due to occlusions and partial views. In this setting, the shapes to be retrieved may undergo a variety of transformations simultaneously, such as non-rigid deformations (changes in pose), topological noise, and missing parts - a combination of nuisance factors that renders the retrieval process extremely challenging. With this benchmark, we aim to evaluate the state of the art in deformable shape retrieval under such kind of transformations. The benchmark is organized in two sub-challenges exemplifying different data modalities (3D vs. 2.5D). A total of 15 retrieval algorithms were evaluated in the contest; this paper presents the details of the dataset, and shows thorough comparisons among all competing methods.
Description

        
@inproceedings{
10.2312:3dor.20171057
, booktitle = {
Eurographics Workshop on 3D Object Retrieval
}, editor = {
Ioannis Pratikakis and Florent Dupont and Maks Ovsjanikov
}, title = {{
Deformable Shape Retrieval with Missing Parts
}}, author = {
RodolĂ , E.
 and
Cosmo, L.
 and
Duong, A.-D.
 and
Furuya, T.
 and
Gasparetto, A.
 and
Hong, Y.
 and
Kim, J.
 and
Saux, B. Le
 and
Litman, R.
 and
Masoumi, M.
 and
Minello, G.
 and
Nguyen, H.-D.
 and
Litany, O.
 and
Nguyen, V.-T.
 and
Ohbuchi, R.
 and
Pham, V.-K.
 and
Phan, T. V.
 and
Rezaei, M.
 and
Torsello, A.
 and
Tran, M.-T.
 and
Tran, Q.-T.
 and
Truong, B.
 and
Wan, L.
 and
Bronstein, M. M.
 and
Zou, C.
 and
Bronstein, A. M.
 and
Audebert, N.
 and
Hamza, A. Ben
 and
Boulch, A.
 and
Castellani, U.
 and
Do, M. N.
}, year = {
2017
}, publisher = {
The Eurographics Association
}, ISSN = {
1997-0471
}, ISBN = {
978-3-03868-030-7
}, DOI = {
10.2312/3dor.20171057
} }
Citation
Collections