To solve the problems of mistaken coloring and color bleeding in the current colorization methods, an end-to-end deep neural network is proposed to achieve remote sensing image colorization. First, the multi-scale residual receptive filed net is introduced to extract the key features of source image. Second, a color information recovery network is con-structed by using U-Net, complex residual structure, attention mechanism, sequeeze-and-excitation and pixel-shuffle blocks to obtain color result. NWPU-RESISC45 dataset is chosen for model training and validation. Compared with other color methods, the PSNR value of the proposed method is increased by 6-10 dB on average and the SSIM value is increased by 0.05-0.11. In addition, the proposed method also achieves satisfactory color results on RSSCN7 and AID datasets.
|Translated title of the contribution||Remote Sensing Image Colorization Based on Deep Neural Networks with Multi-Scale Residual Receptive Filed|
|Original language||Chinese (Traditional)|
|Number of pages||10|
|Journal||Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics|
|State||Published - 20 Nov 2021|