One-Two-One Networks For Compression Artifacts Reduction In Remote Sensing
Keywords
Compression artifacts reduction; Deep learning; One-two-one network; Remote sensing
Abstract
Compression artifacts reduction (CAR) is a challenging problem in the field of remote sensing. Most recent deep learning based methods have demonstrated superior performance over the previous hand-crafted methods. In this paper, we propose an end-to-end one-two-one (OTO) network, to combine different deep models, i.e., summation and difference models, to solve the CAR problem. Particularly, the difference model motivated by the Laplacian pyramid is designed to obtain the high frequency information, while the summation model aggregates the low frequency information. We provide an in-depth investigation into our OTO architecture based on the Taylor expansion, which shows that these two kinds of information can be fused in a nonlinear scheme to gain more capacity of handling complicated image compression artifacts, especially the blocking effect in compression. Extensive experiments are conducted to demonstrate the superior performance of the OTO networks, as compared to the state-of-the-arts on remote sensing datasets and other benchmark datasets. The source code will be available here: https://github.com/bczhangbczhang/.
Publication Date
11-1-2018
Publication Title
ISPRS Journal of Photogrammetry and Remote Sensing
Volume
145
Number of Pages
184-196
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1016/j.isprsjprs.2018.01.003
Copyright Status
Unknown
Socpus ID
85042096911 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85042096911
STARS Citation
Zhang, Baochang; Gu, Jiaxin; Chen, Chen; Han, Jungong; and Su, Xiangbo, "One-Two-One Networks For Compression Artifacts Reduction In Remote Sensing" (2018). Scopus Export 2015-2019. 9055.
https://stars.library.ucf.edu/scopus2015/9055