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

杨利霞

Transferred Multi-Perception Attention Networks for

Remote Sensing Image Super-Resolution

) ]4 T9 j( Y! m2 K$ l
! P$ o9 W; X- M4 t2 N8 o
Image 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
) @7 ~$ w/ D( F0 H4 emany SR methods have been proposed over the last few years, further research is needed to improve
* B" h" L1 F  A) n" I0 @, rSR processes with regard to the complex spatial distribution of the remote sensing images and the
( A% Y( U* ~* Ddiverse 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
0 a7 Y8 _& v5 ]/ |# P2 g4 @* d(RCAG), MPSR can super-resolve low-resolution remote sensing images via multi-perception learning
; @. l( @' T$ `4 W  J/ j# I$ Land multi-level information adaptive weighted fusion. Moreover, a pre-train and transfer learning
, {: C/ s. ~* sstrategy 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
; i6 @0 o; S% N. ^4 D- @; Rdataset and benchmark natural image sets. The proposed model proved its excellence in both objective
criterion and subjective perspective.


) ^4 N' @. A/ x! n9 m4 u