|
Persistent Identifier
|
perma:LIST.WYOUFS |
|
Publication Date
|
2026-07-06 |
|
Title
| Optical Image-to-Image Translation Using Denoising Diffusion Models: Heterogeneous Change Detection as a Use Case [* Cross-Reference *] |
|
Other Identifier
| https://doi.org/10.36227/techrxiv.171328129.97828901/v1
OpenAlex ID: https://openalex.org/W4394855779 |
|
Author
| João Gabriel Vinholi (Instituto Tecnológico de Aeronáutica, Universidade Federal de Santa Catarina, Luxembourg Institute of Science and Technology) - ORCID: https://orcid.org/0000-0002-7887-3018
Marco Chini (Instituto Tecnológico de Aeronáutica, Universidade Federal de Santa Catarina, Luxembourg Institute of Science and Technology) - ORCID: https://orcid.org/0000-0002-9094-0367
Anis Amziane (Instituto Tecnológico de Aeronáutica, Universidade Federal de Santa Catarina, Luxembourg Institute of Science and Technology) - ORCID: https://orcid.org/0000-0002-2480-9205
Renato Machado (Instituto Tecnológico de Aeronáutica, Universidade Federal de Santa Catarina, Luxembourg Institute of Science and Technology) - ORCID: https://orcid.org/0000-0003-0856-5391
Danilo Silva (Instituto Tecnológico de Aeronáutica, Universidade Federal de Santa Catarina, Luxembourg Institute of Science and Technology) - ORCID: https://orcid.org/0000-0001-6290-7968
Patrick Matgen (Instituto Tecnológico de Aeronáutica, Universidade Federal de Santa Catarina, Luxembourg Institute of Science and Technology) - ORCID: https://orcid.org/0000-0001-6668-4693 |
|
Point of Contact
|
Use email button above to contact.
LIST QDKM (LIST) |
|
Description
| We introduce an innovative deep learning-based method that uses a denoising diffusion-based model to translate low-resolution images to high-resolution ones from different optical sensors while preserving the contents and avoiding undesired artifacts. The proposed method is trained and tested on a large and diverse data set of paired Sentinel-II and Planet Dove images. We show that it can solve serious image generation issues observed when the popular classifier-free guided Denoising Diffusion Implicit Model (DDIM) framework is used in the task of Image-to-Image Translation of multi-sensor optical remote sensing images and that it can generate large images with highly consistent patches, both in colors and in features. Moreover, we demonstrate how our method improves heterogeneous change detection results in two urban areas: Beirut, Lebanon, and Austin, USA. Our contributions are: i) a new training and testing algorithm based on denoising diffusion models for optical image translation; ii) a comprehensive image quality evaluation and ablation study; iii) a comparison with the classifier-free guided DDIM framework; and iv) change detection experiments on heterogeneous data. (2024-04-16)
***This entry has been automatically imported via OpenAlex by LIST harvest scripts. Please refer to https://doi.org/10.36227/techrxiv.171328129.97828901/v1 for the original and latest version of the publication*** (2026-07-01) |
|
Subject
| Computer and Information Science; Physics |
|
Keyword
| Computer science
Inpainting
Artificial intelligence
Image translation
Noise reduction
Computer vision
Deep learning
Pattern recognition (psychology)
Translation (biology)
Classifier (UML)
Image (mathematics) |
|
Topic Classification
| Image and Signal Denoising Methods
Advanced Image Processing Techniques
Generative Adversarial Networks and Image Synthesis |
|
Deposit Date
| 2024-04-16 |
|
Data Type
| Preprint |
