Deep High-order Tensor Convolutional Sparse Coding for Stereo Matching

With the rapid development of science and technology, high-dimensional data emerge one after another. High-order tensors can be used to describe high-dimensional data structure, which can retain the hidden structure of data, but cannot obtain the deep features. Therefore, it is very important to est...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2021 3rd International Conference on Robotics and Computer Vision (ICRCV) S. 57 - 62
Hauptverfasser: Cui, Wenjing, Cheng, Chunbo
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 06.08.2021
Schlagworte:
Computer vision
Convolutional codes
convolutional sparse coding
Costs
Data structures
Deep learning
dictionary learning
Encoding
high-order tensor
stereo matching
Tensors
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:With the rapid development of science and technology, high-dimensional data emerge one after another. High-order tensors can be used to describe high-dimensional data structure, which can retain the hidden structure of data, but cannot obtain the deep features. Therefore, it is very important to establish a deep high order tensor model. In this paper, we propose a deep high-order tensor convolutional sparse coding model, which can automatically learn the deep convolutional kernel. Based on the learned deep convolutional kernel, a two-layer deep dictionary learning model is established. Then, the sparse representation coefficients are respectively solved, and a new weighted matching cost method is constructed, which combines shallow and deep features. The experimental results on the Middlebury 2014 dataset show that the proposed deep high-order tensor convolutional sparse coding is effective for stereo matching.
DOI:10.1109/ICRCV52986.2021.9546963