Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zeraatkar, Ehsan, Faroughi, Salah, Tešić, Jelena
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2502.06741
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918033037983744
author Zeraatkar, Ehsan
Faroughi, Salah
Tešić, Jelena
author_facet Zeraatkar, Ehsan
Faroughi, Salah
Tešić, Jelena
contents Purpose: Earth system models (ESMs) integrate the interactions of the atmosphere, ocean, land, ice, and biosphere to estimate the state of regional and global climate under a wide variety of conditions. The ESMs are highly complex; thus, deep neural network architectures are used to model the complexity and store the down-sampled data. This paper proposes the Vision Transformer Sinusoidal Representation Networks (ViSIR) to improve the ESM data's single image SR (SR) reconstruction task. Methods: ViSIR combines the SR capability of Vision Transformers (ViT) with the high-frequency detail preservation of the Sinusoidal Representation Network (SIREN) to address the spectral bias observed in SR tasks. Results: The ViSIR outperforms SRCNN by 2.16 db, ViT by 6.29 dB, SIREN by 8.34 dB, and SR-Generative Adversarial (SRGANs) by 7.93 dB PSNR on average for three different measurements. Conclusion: The proposed ViSIR is evaluated and compared with state-of-the-art methods. The results show that the proposed algorithm is outperforming other methods in terms of Mean Square Error(MSE), Peak-Signal-to-Noise-Ratio(PSNR), and Structural Similarity Index Measure(SSIM).
format Preprint
id arxiv_https___arxiv_org_abs_2502_06741
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ViSIR: Vision Transformer Single Image Reconstruction Method for Earth System Models
Zeraatkar, Ehsan
Faroughi, Salah
Tešić, Jelena
Computer Vision and Pattern Recognition
Purpose: Earth system models (ESMs) integrate the interactions of the atmosphere, ocean, land, ice, and biosphere to estimate the state of regional and global climate under a wide variety of conditions. The ESMs are highly complex; thus, deep neural network architectures are used to model the complexity and store the down-sampled data. This paper proposes the Vision Transformer Sinusoidal Representation Networks (ViSIR) to improve the ESM data's single image SR (SR) reconstruction task. Methods: ViSIR combines the SR capability of Vision Transformers (ViT) with the high-frequency detail preservation of the Sinusoidal Representation Network (SIREN) to address the spectral bias observed in SR tasks. Results: The ViSIR outperforms SRCNN by 2.16 db, ViT by 6.29 dB, SIREN by 8.34 dB, and SR-Generative Adversarial (SRGANs) by 7.93 dB PSNR on average for three different measurements. Conclusion: The proposed ViSIR is evaluated and compared with state-of-the-art methods. The results show that the proposed algorithm is outperforming other methods in terms of Mean Square Error(MSE), Peak-Signal-to-Noise-Ratio(PSNR), and Structural Similarity Index Measure(SSIM).
title ViSIR: Vision Transformer Single Image Reconstruction Method for Earth System Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.06741