MapGen-Diff: An End-to-End Remote Sensing Image to Map Generator via Denoising Diffusion Bridge Model
Remote Sensing · 06.10.2024 · 16 (19) · 3716
DOI: 10.3390/rs16193716 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 06.10.2024. Verfasst von Jilong Tian und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Online maps are of great importance in modern life, especially in commuting, traveling and urban planning. The accessibility of remote sensing (RS) images has contributed to the widespread practice of generating online maps based on RS images. The previous works leverage an idea of domain mapping to achieve end-to-end remote sensing image-to-map translation (RSMT). Although existing methods are effective and efficient for online map generation, generated online maps still suffer from ground features distortion and boundary inaccuracy to a certain extent. Recently, the emergence of diffusion models has signaled a significant advance in high-fidelity image synthesis. Based on rigorous mathematical theories, denoising diffusion models can offer controllable generation in sampling process, which are very suitable for end-to-end RSMT. Therefore, we design a novel end-to-end diffusion model to generate online maps directly from remote sensing images, called MapGen-Diff. We leverage a strategy inspired by Brownian motion to make a trade-off between the diversity and the accuracy of generation process. Meanwhile, an image compression module is proposed to map the raw images into the latent space for capturing more perception features. In order to enhance the geometric accuracy of ground features, a consistency regularization is designed, which allows the model to generate maps with clearer boundaries and colorization. Compared to several state-of-the-art methods, the proposed MapGen-Diff achieves outstanding performance, especially a 5% RMSE and 7% SSIM improvement on Los Angeles and Toronto datasets. The visualization results also demonstrate more accurate local details and higher quality.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Tian, J., Wu, J., Chen, H., & Ma, M. (2024). MapGen-Diff: An End-to-End Remote Sensing Image to Map Generator via Denoising Diffusion Bridge Model. Remote Sensing, 16(19), 3716. https://doi.org/10.3390/rs16193716
Vancouver
Tian J, Wu J, Chen H, Ma M. MapGen-Diff: An End-to-End Remote Sensing Image to Map Generator via Denoising Diffusion Bridge Model. Remote Sensing. 2024;16(19):3716. doi:10.3390/rs16193716
BibTeX
@article{Tian2024,
author = {Tian, Jilong and Wu, Jiangjiang and Chen, Hao and Ma, Mengyu},
title = {MapGen-Diff: An End-to-End Remote Sensing Image to Map Generator via Denoising Diffusion Bridge Model},
journal = {Remote Sensing},
year = {2024},
volume = {16},
number = {19},
pages = {3716},
doi = {10.3390/rs16193716}
}
EUVIMED