Evaluating Combinations of Optimizers and Loss Functions for Cloud Removal Using Diffusion Models

Leandro Silva, Leandro Silva, João Mari, Mauricio Escarpinati, André Backes

2025

Abstract

Cloud removal is crucial for photogrammetry applications, including urban planning, precision agriculture, and climate monitoring. Recently, generative models, especially those based on latent diffusion, have shown remarkable results in high-quality synthetic image generation, making them suitable for cloud removal tasks. These approaches require optimizing numerous trainable parameters with various optimizers and loss functions. This study evaluates the impact of combining three optimizers (SGD, Adam, and AdamW) with the MAE, MSE, and Huber loss functions. For evaluation, we used the SEN MTC New dataset, which contains pairs of 4-band images with and without clouds, divided into training, validation, and test sets. The results, measured in terms of PSNR and SSIM, show that the diffusion model combining AdamW and the Huber loss function delivers exceptional performance in cloud removal.

Paper Citation

in Harvard Style

Silva L., Mari J., Escarpinati M. and Backes A. (2025). Evaluating Combinations of Optimizers and Loss Functions for Cloud Removal Using Diffusion Models. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 648-656. DOI: 10.5220/0013252100003912

in Bibtex Style

@conference{visapp25,
author={Leandro Silva and João Mari and Mauricio Escarpinati and André Backes},
title={Evaluating Combinations of Optimizers and Loss Functions for Cloud Removal Using Diffusion Models},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={648-656},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013252100003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Evaluating Combinations of Optimizers and Loss Functions for Cloud Removal Using Diffusion Models
SN - 978-989-758-728-3
AU - Silva L.
AU - Mari J.
AU - Escarpinati M.
AU - Backes A.
PY - 2025
SP - 648
EP - 656
DO - 10.5220/0013252100003912
PB - SciTePress