DEEP SPARSE DICTIONARY-BASED REPRESENTATION FOR 3D NON-RIGID SHAPE RETRIEVAL

被引：3

作者：

Mohamed, Hela Haj ^{[1
]}

Belaid, Samir ^{[1
]}

Naanaa, Wady ^{[2
]}

Ben Romdhane, Lotfi ^{[1
]}

机构：

[1] Univ Sousse, MARS Res Lab, Sousse, Tunisia

[2] Univ Tunis El Manar Tunisia, Tunis, Tunisia

来源：

36TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2021 | 2021年

关键词：

Non-rigid 3D shape retrieval; Deep sparse descriptor; Sparse coding; dictionary leaning; deep learning; VARIABLE SELECTION; DESCRIPTORS; ALGORITHM; FEATURES; OBJECT;

D O I：

10.1145/3412841.3441984

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we address the problem of non-rigid 3D shape retrieval. The proposed method extract high-level features that are invariant to non-rigid shape deformations by integrating deep dictionary learning and a sparse coding approach. A stacked sparse coding network is constructed to achieve a multiple layers dictionary learning instead of a single level dictionary learning. Then, for a given 3D query, a 3D shape descriptor is calculated, providing a multi-scale shape representations. This descriptor is, therefore, used to access deep learned dictionary. The proposed method is validated on two benchmarks, namely Shrec'11 and Shrec'15, for 3D non-rigid object retrieval and compared with existing deep learning-based approaches.

引用

页码：1070 / 1077

页数：8

共 37 条

[1] K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation [J].