Transferred Multi-Perception Attention Networks for Remote Sensing Image Supe...

杨利霞

Transferred Multi-Perception Attention Networks for

Remote Sensing Image Super-Resolution

# e* K# s8 f3 d4 M- G7 S% j
  P6 t9 s/ g# \5 fImage super-resolution (SR) reconstruction plays a key role in coping with the increasing
demand on remote sensing imaging applications with high spatial resolution requirements. Though
5 N+ Q. A' ]: X) K+ ^many SR methods have been proposed over the last few years, further research is needed to improve
' G, U7 r* x% o  ?- PSR processes with regard to the complex spatial distribution of the remote sensing images and the
diverse spatial scales of ground objects. In this paper, a novel multi-perception attention network
(MPSR) is developed with performance exceeding those of many existing state-of-the-art models.
By incorporating the proposed enhanced residual block (ERB) and residual channel attention group
(RCAG), MPSR can super-resolve low-resolution remote sensing images via multi-perception learning
and multi-level information adaptive weighted fusion. Moreover, a pre-train and transfer learning
strategy is introduced, which improved the SR performance and stabilized the training procedure.
Experimental comparisons are conducted using 13 state-of-the-art methods over a remote sensing
- f- \' ?7 k- j$ Ydataset and benchmark natural image sets. The proposed model proved its excellence in both objective
criterion and subjective perspective.
5 q9 _3 H  m0 Y8 P