A multitemporal remote sensing thick cloud removal network based on implicit reconstruction

Thick clouds reduce the useful information in visible remote sensing and restrict the usefulness of remote sensing images. Many scholars have proposed time-based strategies to solve these restrictions. However, these approaches still suffered from difficulties, such as requiring paired cloud mask pictures as additional auxiliary images, having artefacts or image distortions, and model training difffculties. For thick clouds in multitemporal remote sensing, this research offers an implicit multitemporal remote sensing thick cloud removal network (IRNet). As the name suggests, IRNet does not need cloud masks as external auxiliary data inputs to the network. To attenuate the temporal difference problem between multitemporal remote sensing images with model training difffculties, multiscale feature extraction block (MFEB) is designed in IRNet. In addition, the designed upsampling and convolution blocks are utilized in the designed high-fidelity reconstruction block (HFRB) to reconstruct the missing information under the cloud to generate highly preserved cloud-free images. By utilizing two readily datasets for removing multitemporal thick clouds, we have evaluated our method against the most effective existing techniques. Our findings consistently demonstrate that our method improves the restoration of texture detail and spatial information.