Hyperspectral remote sensing images (HSIs) have been applied in urban planning, environmental monitoring, and other fields. However, they are susceptible to noise interference, such as Gaussian noise, stripe, and mixed noises, from various factors in the imaging process, which greatly limits their applications. Although previous efforts to improve HSI quality have achieved remarkable results, there are still many challenges to be solved. To avoid the poor generalization ability and improve the stripe removal performance of the network in real scenarios, in this article, we proposed a novel deep learning model (Translution-SNet) for HSI stripe noise removal based on a semisupervised training strategy that applies a convolution and transformer for feature extraction. Moreover, we used an unbiased estimation method to calculate the loss function of the unsupervised part from noisy data without a clean image. The semisupervised method improved the ability of Translution-SNet to deal with various complex stripe noises during stripe removal and strengthened its robustness and generalization ability. Our experimental results showed that Translution-SNet could robustly handle stripe noise of images with different loads and achieve satisfactory results, proving its feasibility and effectiveness. In addition, Translution-SNet showed good generalization ability.

The ice, cloud, and land elevation satellite-2 (ICESat-2) is equipped with a photon-counting laser altimeter system and demonstrates outstanding ability to measure elevations in the ever-changing earth. However, the ICESat-2 data contain several noise photons affected by solar returns, and there are no reference data of signal or noise photons for evaluating the performance of denoising algorithms. In this letter, we propose a self-adaptive denoising algorithm based on a genetic algorithm (SADA-GA) for the ICESat-2 data, which uses the real-coded genetic algorithm to adaptively search for the global optimal denoising parameters in different data sets. The SADA-GA addresses the limitation of the selection method of the two parameters K and T in the localized statistics-based algorithm that normally cannot be applied to different data sets. To evaluate the algorithm performance, we created an ICESat-2 data set named WHU-PCL and compared the SADA-GA with two classic methods. The qualitative and quantitative analyses showed that our method can extract signal photons more efficiently from different ICESat-2 data sets and achieve the $F$ value of 0.99 in nighttime data. In addition, we analyzed the factors that affect the SADA-GA performance and found that the signal-to-noise ratio (SNR) is the most important parameter.

GaoFen-3 (GF-3) is a C-band multipolarization synthetic aperture radar (SAR) satellite with 12 imaging modes. However, its initial positioning accuracy remains unsatisfactory, thereby hindering its use for large-area surveying and mapping. This study proposes a block orthorectification method without ground control points (GCPs) using the GF-3 Fine strip II (FSII) mode. To address the challenges with the accuracy and efficiency of this method, an integrated block orthorectification method was developed to conduct integrated processing of large-scale GF-3 satellite images without GCPs. Geometric calibration was used to improve the absolute positioning accuracy of each SAR image. Then, several tie points (TPs) were extracted using the SAR scale-invariant feature transform (SIFT) operator. A parallel matching strategy was used in the block images registration. The block adjustment model was constructed to solve the orientation parameter of all SAR images. The experimental results of 1,468 GF-3 images of China’s entire land area show a TPs root-mean-square error of 0.724 pixel and 8.014 m for the independent checkpoint, suggesting that the proposed method can effectively improve the geometric accuracy of GF-3 satellite images and demonstrate the feasibility of large-scale SAR mapping without GCPs.