High-mountain water bodies represent critical components of their ecosystems, serving as vital freshwater reservoirs, environmental regulators, and sentinels of climate change. To understand the environmental dynamics of these regions, comprehensive analyses of lakes across spatial and temporal scales are necessary. While remote sensing offers a powerful tool for lake monitoring, applications in high-mountain terrain present unique challenges. The Ancash and Cuzco regions of the Peruvian Andes exemplify these challenges. These regions harbor numerous high-mountain lakes, which are crucial for fresh water supply and environmental regulation. This paper presents an exploratory examination of remote sensing techniques for lake monitoring in the Ancash and Cuzco regions of the Peruvian Andes. The study compares three deep learning models for lake segmentation: the well-established DeepWaterMapV2 and WatNet models and the adapted WaterSegDiff model, which is based on a combination of diffusion and transformation mechanisms specifically conditioned for lake segmentation. In addition, the Normalized Difference Water Index (NDWI) with Otsu thresholding is used for comparison purposes. To capture lakes across these regions, a new dataset was created with Landsat-8 multispectral imagery (bands 2–7) from 2013 to 2023. Quantitative and qualitative analyses were performed using metrics such as Mean Intersection over Union (MIoU), Pixel Accuracy (PA), and F1 Score. The results achieved indicate equivalent performance of DeepWaterMapV2 and WatNet encoder–decoder architectures, achieving adequate lake segmentation despite the challenging geographical and atmospheric conditions inherent in high-mountain environments. In the qualitative analysis, the behavior of the WaterSegDiff model was considered promising for the proposed application. Considering that WatNet is less computationally complex, with 3.4 million parameters, this architecture becomes the most pertinent to implement. Additionally, a detailed temporal analysis of Lake Singrenacocha in the Vilcanota Mountains was conducted, pointing out the more significant behavior of the WatNet model.

High Dynamic Range (HDR) image reconstruction has gained prominence in a wide range of fields; not only is it implemented in computer vision, but industries such as entertainment and medicine also benefit considerably from this technology due to its ability to capture and reproduce scenes with a greater variety of luminosities, extending conventional levels of perception. This article presents a review of the state of the art of HDR reconstruction methods based on deep learning, ranging from classical approaches that are still expressive and relevant to more recent proposals involving the advent of new architectures. The fundamental role of high-quality datasets and specific metrics in evaluating the performance of HDR algorithms is also discussed, as well as emphasizing the challenges inherent in capturing multiple exposures and dealing with artifacts. Finally, emerging trends and promising directions for overcoming current limitations and expanding the potential of HDR reconstruction in real-world scenarios are highlighted.

Printed circuit boards (PCBs) are key components in the electronics industry, and ensuring their integrity is essential for reliable manufacturing. Automated inspection systems based on computer vision, although efficient, face challenges. In this scenario, deep learning techniques have become effective solutions for detecting defects in more modern and complex PCBs. This article presents a comparative study between the YOLOv8n, YOLOv11n and RT-DETRv2 models for identifying defects in PCBs. The experiments were conducted using the PKU-Market-PCB dataset, which includes Missing Hole, Mouse Bite, Open Circuit, Short Circuit, Spur and Spurious Copper defects. To reduce the computational cost, modified versions of YOLOv8n and YOLOv11n with Depthwise convolution blocks (YOLOv8-DWConv and YOLOv11-DWConv). The analysis includes quantitative and qualitative comparisons. In addition, the robustness of the models is evaluated under challenging conditions with blur and illumination gradient noise. The results indicate that YOLOv11n achieves the best overall performance, while YOLOv11n-DWConv offers a competitive balance between precision and computational efficiency.

Land Surface Temperature (LST) monitoring is a key factor in demonstrating global climate change. Considering that cloud cover often obscures accurate remotely sensed LST data, it is important to develop approaches to reconstruct occluded areas. This paper presents an inpainting technique, designated RePaint, which utilizes Denoising Diffusion Probabilistic Models (DDPM) for the removal of clouds and the retrieval of LST data from Landsat-8 remote sensing imagery. The DDPM was trained with cloud-free LST image patches, and binary masks were formed by the segmentation process using the Ukis Cloud Shadow Mask to condition the region to be reconstructed. To simulate cloud occlusion in the test data, three cloud cover scenarios with 15%, 22% and 50% missing rate data were investigated. The performance of the approach was evaluated through a combination of quantitative and qualitative assessments. The quantitative analysis showed that the model exhibited consistent performance during the reconstruction process, achieving a mean squared error 0.0001, a peak signal to noise ratio 41.2888, and a structural similarity index 0.9826. In order to provide a more comprehensive visual representation of the results, boxplots and the Gaussian distribution of the temperature error in the LST reconstruction were included. Images of the absolute error of the reconstruction and scatterplots were used for qualitative analysis of randomly selected LST patches. The results demonstrate that the characteristics of the land surface have been preserved, exhibiting a minimum incidence of temperature reconstruction error and spatial coherence across all scenarios.

Denoising diffusion probabilistic models (DDPMs) have demonstrated significant potential in addressing complex image processing challenges. This paper explores the application of DDPMs in three different areas: reconstruction of remote sensing imagery affected by cloud cover, reconstruction of facial images with occluded areas, and segmentation of bodies of water from remote sensing imagery. Inpainting involves filling in missing regions in images, while DDPMs act as data generators capable of synthesizing information that alings coherently with the context of the original data. Inspired by the inpainting technique, the RePaint approach was adapted and applied to reconstruction tasks. The WaterSegDiff approach, which uses a diffusion model as a backbone, was employed for the segmentation task. To illustrate the model’s behavior and provide examples of the tasks, experiments were carried out with both qualitative and quantitative evaluations. The qualitative results show the model’s ability to generate data for reconstruction and segmentation. Quantitatively, metrics such as MSE, PSNR, SSIM, IoU, PA and F1 score highlight the model’s proficient performance in image processing tasks. In this scenario, DDPMs have proved to be a promising tool for high-quality data reconstruction, enabling the hallucination of image regions with high visual coherence and facilitating applications in various areas, such as environmental monitoring, facial recognition, water resource mapping, among others.

Multi-exposure high dynamic range (HDR) image reconstruction makes it possible to improve the quality of low dynamic range (LDR) images using algorithms based on deep learning. The main challenge in this task lies in the generation of ghosting artifacts in the resulting image, caused by the displacement of objects and by the low or overexposure in the input LDR images. To overcome this challenge, this paper proposes the FLASH-S architecture, which incorporates an innovative attention block using Vision Mamba state-space models (SSM) to enhance the extracted features from the input images. The features are serialized in four different directions to guarantee the same importance in each patch of the sequence in the SSM. In addition, the FLASH architecture was proposed, an improved version of FLASH-S using optical flow to align the input images. Experiments were carried out using the Kalantari, SynHDR and Tursun datasets. Based on seven quality metrics and three computational cost metrics, the results showed that the FLASH-S and FLASH proposals are superior to state-of-the-art algorithms. Additionally, FLASH demonstrated better reconstruction quality in qualitative evaluations, generalization capacity and tests in real environments. The model’s source code can be obtained from: https://github.com/pavic-lab-ufac/FLASH.