MASCAR: Multidomain Adaptive Spatial–Spectral Variable Compression Artifact Removal Network for Multispectral Remote Sensing Images

Jaemyung Kim, Hyun-Ho Kim, Doo-Chun Seo, Jae-Heon Jeong, Jin-Ku Kang, Yongwoo Kim

Abstract: In remote sensing environments, image compression is essential to efficiently transmit and store high-resolution images due to the limited bandwidth and storage capacity. However, compression often leads to image quality degradation, requiring compression artifact removal technology in the postprocessing stage. Although deep neural networks have shown remarkable performance in image restoration, most existing methods have not adequately considered the compression conditions specific to remote sensing environments and have been evaluated primarily on synthetic datasets. To solve these issues, we propose a multidomain adaptive spatial–spectral variable compression artifact removal network (MASCAR) that effectively restores the earth surface details of compressed images in remote sensing environments. We introduce a multidomain local-patch collaborative learning strategy that extracts diverse features by decomposing the input local patch into different domains. In addition, we propose a detail focusing approach to direct the network’s focus toward fine-texture detail restoration and ensure stable training of remote sensing images with significant deviations in pixel distribution of local patches. Furthermore, a detail enhancement approach is presented to enhance the details of the restored images. Moreover, we propose an incorporated compressed image quality adaptation mechanism to respond flexibly to unknown compression ratios in remote sensing environments. The performance of MASCAR applied with the proposed method is evaluated on synthetic and real-world remote sensing datasets. Experimental results demonstrate that the proposed method has better quantitative performance and visual quality than existing methods.

External IDs:doi:10.1109/tgrs.2023.3347518