2023/09/28 by Orkhan Baghirli, Hamid Askarov, Baghirli, Orkhan +7 · 3 citations
Computer Science · Engineering · #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Data mining #Deep learning #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Machine learning #Medical Image Segmentation Techniques #Probabilistic logic #Remote-Sensing Image Classification #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2309.16812
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/09/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep learning models in the Earth Observation domain heavily rely on the availability of large-scale accurately labeled satellite imagery. However, obtaining and labeling satellite imagery is a resource-intensive endeavor. While generative models offer a promising solution to address data scarcity, their potential remains underexplored. Recently, Denoising Diffusion Probabilistic Models (DDPMs) have demonstrated significant promise in synthesizing realistic images from semantic layouts. In this paper, a conditional DDPM model capable of taking a semantic map and generating high-quality, diverse, and correspondingly accurate satellite images is implemented. Additionally, a comprehensive illustration of the optimization dynamics is provided. The proposed methodology integrates cutting-edge techniques such as variance learning, classifier-free guidance, and improved noise scheduling. The denoising network architecture is further complemented by the incorporation of adaptive normalization and self-attention mechanisms, enhancing the model's capabilities. The effectiveness of our proposed model is validated using a meticulously labeled dataset introduced within the context of this study. Validation encompasses both algorithmic methods such as Frechet Inception Distance (FID) and Intersection over Union (IoU), as well as a human opinion study. Our findings indicate that the generated samples exhibit minimal deviation from real ones, opening doors for practical applications such as data augmentation. We look forward to further explorations of DDPMs in a wider variety of settings and data modalities. An open-source reference implementation of the algorithm and a link to the benchmarked dataset are provided at https://github.com/obaghirli/syn10-diffusion.