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

杨利霞

Transferred Multi-Perception Attention Networks for

0 q$ |# F3 i3 \4 {1 v2 m

Remote Sensing Image Super-Resolution

  W  I9 H( F9 I( ^/ p9 m* A


6 A  t/ Y) l' v# }% q9 Q6 ^& _6 OImage 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
: f' v9 d& ~2 `( L: K2 q' E! A; Lmany SR methods have been proposed over the last few years, further research is needed to improve
2 g" y1 d& u- _2 o  [' ~6 i- 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.
+ W/ O8 F6 ~4 g7 l6 LBy 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
; @2 Y. ?2 N' qand 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.
% Y: F1 v3 g( F4 k6 y1 y% g% dExperimental comparisons are conducted using 13 state-of-the-art methods over a remote sensing
dataset and benchmark natural image sets. The proposed model proved its excellence in both objective
. f1 n# u2 w7 d. \) rcriterion and subjective perspective.