In remote sensing applications, pixel-level cloud masks are indispensable in various specific tasks. Consequently, cloud detection is typically categorized as a semantic segmentation task within the domain of RS image processing. It aims to identify the presence or absence of clouds on a per-pixel basis. We integrate some diffusion models into comparisons to explore the differences in diffusion model performance across medical or natural image segmentation and cloud detection tasks in remote sensing images.
Here is a reference implementation on Python and Pytorch.
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model link
DDP: Diffusion Model for Dense Visual Predictionlink
Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation: link