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

杨利霞

Transferred Multi-Perception Attention Networks for

8 Q& P- n' H, j

Remote Sensing Image Super-Resolution

. Z1 q7 T) ?$ m# |- k
: C6 o9 B" V  p1 k
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
( s1 K% G/ q4 i4 Rmany SR methods have been proposed over the last few years, further research is needed to improve
/ `7 D, H. _* f* L4 YSR 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
0 d8 o" C7 Q* c7 }. `5 a4 M(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
# D7 J+ ^7 |' pand 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
* v6 t& Q! a' m2 r$ ~' `% pdataset and benchmark natural image sets. The proposed model proved its excellence in both objective
8 X3 f( h+ q- b* }: g4 }3 icriterion and subjective perspective.


) U' S. N& N, Z8 @2 [6 h