The existence of clouds is one of the main factors that contributes to missing information in optical remote sensing images, restricting their further applications for Earth observation, so how to reconstruct the missing information caused by clouds is of great concern. Inspired by the image-to-image translation work based on convolutional neural network model and the heterogeneous information fusion thought, we propose a novel cloud removal method in this paper. The approach can be roughly divided into two steps: in the first step, a specially designed convolutional neural network (CNN) translates the synthetic aperture radar (SAR) images into simulated optical images in an object-to-object manner; in the second step, the simulated optical image, together with the SAR image and the optical image corrupted by clouds, is fused to reconstruct the corrupted area by a generative adversarial network (GAN) with a particular loss function. Between the first step and the second step, the contrast and luminance of the simulated optical image are randomly altered to make the model more robust. Two simulation experiments and one real-data experiment are conducted to confirm the effectiveness of the proposed method on Sentinel 1/2, GF 2/3 and airborne SAR/optical data. The results demonstrate that the proposed method outperforms state-of-the-art algorithms that also employ SAR images as auxiliary data.

Complementary information from multi-sensors can be combined to improve the availability and reliability of stand-alone data. Typically, multispectral (MS) images contain plentiful spectral information of the Earth’s surface that is beneficial for identifying land cover types, while synthetic aperture radar (SAR) images can provide abundant information on the texture and structure of target objects. Therefore, this paper presents a fusion framework to integrate the information from MS and SAR images based on the Laplacian pyramid (LP) and sparse representation (SR) theory. LP is performed to decompose both the multispectral and SAR images into high-frequency components and low-frequency components, so that different processing strategies can be applied to multi-scale information. Low-frequency components are merged based on SR theory, whereas high-frequency components are combined based on a certain activity-level measurement, identifying salient features. Finally, LP reconstruction is performed to obtain the integrated image. We conduct experiments on several datasets to verify the effectiveness of the proposed method. Both visual interpretation and statistical analyses demonstrate that the proposed method strikes a satisfactory balance between spectral information preservation and the enhancement of spatial and textual characteristics. In addition, a further discussion regarding the adjustability property of the proposed method shows its flexibility for further application scenarios.