Deep Generative AI Based on Denoising Diffusion Probabilistic Models for Applications in Image Processing

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.