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

杨利霞

Transferred Multi-Perception Attention Networks for

Remote Sensing Image Super-Resolution

6 o! J- O; p3 U- cImage 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
3 v! V6 S( ?. A. t9 U2 z- jmany SR methods have been proposed over the last few years, further research is needed to improve
$ a6 \7 v) o9 [) t- f& J5 l* GSR 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.
! w" H  h( G, S3 `4 xExperimental comparisons are conducted using 13 state-of-the-art methods over a remote sensing
  ^9 D' l3 V3 \* L1 K1 ?+ |6 q  L! ?dataset and benchmark natural image sets. The proposed model proved its excellence in both objective
6 M% [' L$ p" i1 q  wcriterion and subjective perspective.
- z: r4 P8 A1 M7 E* Z
8 l" R+ Q- w% K& p
2 S9 r. e. X: e4 @) O/ P