In today’s rapidly evolving world, vision models are playing an increasingly crucial role in a variety of applications, including robotics, autonomous driving, healthcare, industrial automation, and environmental monitoring. However, these models often face challenges in dynamic, complex, and resource-constrained environments where data is noisy, incomplete, or continuously evolving.

Cloudy and rainy environments are common in tropical, subtropical, and other regions frequently affected by cloud cover and rainfall. These challenging conditions pose significant obstacles to remote sensing data acquisition, processing, and applications, while also motivating innovation in methodologies and technologies.

Accurate 3D perception in underwater environments has become a critical requirement for various ocean engineering tasks such as subsea infrastructure inspection, autonomous navigation of underwater vehicles, habitat mapping, and environmental monitoring.

Recent interdisciplinary research reveals noise isn’t just a pollutant to remove—under control, it acts as a stimulus/explicit prior to boost model performance (refine decision boundaries, enhance privacy/robustness, support uncertainty quantification). However, existing studies lack a systematic "mitigation-stimulation-exploitation" framework and theoretical basis. This special issue solicits original research on noise-aware remote sensing to share advances and drive its development.

Geospatial image analysis has emerged as a cornerstone for mission-critical applications across diverse domains, ranging from urban modeling (e.g., multi-sensor UAV navigation in degraded visibility) to dynamic environmental monitoring (e.g., near-real-time disaster response), and the rising paradigm of foundation model-driven scene interpretation.

Hyperspectral imaging has emerged as a transformative technology in Earth observation, capturing detailed spectral information across hundreds of narrow, contiguous bands. This rich spectral data enables precise material identification and quantitative analysis, supporting applications in agriculture, environmental monitoring, mineral exploration, and urban planning.

"Sensing Intelligence and Machine Learning" describes the combination of artificial intelligence (AI) and machine learning (ML) approaches with sensor technologies. This fusion improves sensor capabilities, increasing accuracy, sensitivity, and adaptability. Applications for "Sensing Intelligence and Machine Learning" include healthcare and biomedical engineering, environmental monitoring, autonomous vehicles, etc.

This Special Issue seeks breakthroughs in image and video processing, exploring novel uses of cutting-edge data acquisition/visualization devices (like 3D scanners, VR, robotics) and new methodologies for processing large-scale datasets. It highlights modern techniques, including deep learning and hypergraph learning, to advance the state of the art in image analysis.

Over the past decade or so, artificial intelligence technologies represented by deep learning have made remarkable progress, especially in the domains of signal processing and computer vision. In these domains, deep learning-based methods are being iterated and commercialized at an unprecedented rate, dramatically changing the way humans live, learn, and work.