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

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.