A variational autoencoder inspired unsupervised remote sensing image super resolution method with multi-degradation
In current super-resolution (SR) research, blind SR models capable of handling multiple degradations have attracted significant attention. Inspired by variational autoencoders (VAEs) that model data distributions through latent representations, this paper proposes a VAE framework for unsupervised re...
Uložené v:
| Vydané v: | International journal of applied earth observation and geoinformation Ročník 144; s. 104885 |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Elsevier B.V
01.11.2025
Elsevier |
| Predmet: | |
| ISSN: | 1569-8432 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | In current super-resolution (SR) research, blind SR models capable of handling multiple degradations have attracted significant attention. Inspired by variational autoencoders (VAEs) that model data distributions through latent representations, this paper proposes a VAE framework for unsupervised remote sensing image (RSI) SR. VAEs excel at learning rich latent representations, modeling probabilistic distributions of input data and unsupervised learning, making them inherently well-suited to real-world blind SR scenarios. The proposed framework consists of an encoder that maps low-resolution (LR) images into a latent space and a decoder that reconstructs super-resolved images from the latent representations. To enhance latent modeling, an alternating optimization strategy is implemented for training the encoder and decoder. Furthermore, a comprehensive loss function and a latent coding regularization strategy are designed to constrain latent representations while maintaining image domain consistency. Experimental results demonstrate that on synthetic data, our method achieves favorable performance in both visual quality and quantitative metrics. It also demonstrates competitively performance compared to supervised methods, particularly in 4× and 8× SR tasks. Additionally, evaluations on Jilin-1 satellite RSIs further validate the effectiveness of our approach.
•The unsupervised SR method handles multi-degradation with satisfying performance.•The encoder and decoder are trained alternately.•The decoder decodes latent code into SR image with fine details.•Constraining latent code with comprehensive loss improves the SR results.•Regularization strategy improves SR performance on large ratios 4 and 8. |
|---|---|
| AbstractList | In current super-resolution (SR) research, blind SR models capable of handling multiple degradations have attracted significant attention. Inspired by variational autoencoders (VAEs) that model data distributions through latent representations, this paper proposes a VAE framework for unsupervised remote sensing image (RSI) SR. VAEs excel at learning rich latent representations, modeling probabilistic distributions of input data and unsupervised learning, making them inherently well-suited to real-world blind SR scenarios. The proposed framework consists of an encoder that maps low-resolution (LR) images into a latent space and a decoder that reconstructs super-resolved images from the latent representations. To enhance latent modeling, an alternating optimization strategy is implemented for training the encoder and decoder. Furthermore, a comprehensive loss function and a latent coding regularization strategy are designed to constrain latent representations while maintaining image domain consistency. Experimental results demonstrate that on synthetic data, our method achieves favorable performance in both visual quality and quantitative metrics. It also demonstrates competitively performance compared to supervised methods, particularly in 4× and 8× SR tasks. Additionally, evaluations on Jilin-1 satellite RSIs further validate the effectiveness of our approach.
•The unsupervised SR method handles multi-degradation with satisfying performance.•The encoder and decoder are trained alternately.•The decoder decodes latent code into SR image with fine details.•Constraining latent code with comprehensive loss improves the SR results.•Regularization strategy improves SR performance on large ratios 4 and 8. In current super-resolution (SR) research, blind SR models capable of handling multiple degradations have attracted significant attention. Inspired by variational autoencoders (VAEs) that model data distributions through latent representations, this paper proposes a VAE framework for unsupervised remote sensing image (RSI) SR. VAEs excel at learning rich latent representations, modeling probabilistic distributions of input data and unsupervised learning, making them inherently well-suited to real-world blind SR scenarios. The proposed framework consists of an encoder that maps low-resolution (LR) images into a latent space and a decoder that reconstructs super-resolved images from the latent representations. To enhance latent modeling, an alternating optimization strategy is implemented for training the encoder and decoder. Furthermore, a comprehensive loss function and a latent coding regularization strategy are designed to constrain latent representations while maintaining image domain consistency. Experimental results demonstrate that on synthetic data, our method achieves favorable performance in both visual quality and quantitative metrics. It also demonstrates competitively performance compared to supervised methods, particularly in 4× and 8× SR tasks. Additionally, evaluations on Jilin-1 satellite RSIs further validate the effectiveness of our approach. |
| ArticleNumber | 104885 |
| Author | Wang, Yongcheng Li, Gang Xu, Dongdong Werner, Martin Zhang, Ning |
| Author_xml | – sequence: 1 givenname: Ning orcidid: 0000-0002-1920-0649 surname: Zhang fullname: Zhang, Ning organization: Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China – sequence: 2 givenname: Yongcheng orcidid: 0000-0002-1647-2956 surname: Wang fullname: Wang, Yongcheng organization: Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, 130033, China – sequence: 3 givenname: Gang surname: Li fullname: Li, Gang email: gangli@mail.tsinghua.edu.cn organization: Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China – sequence: 4 givenname: Dongdong surname: Xu fullname: Xu, Dongdong organization: Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, 130033, China – sequence: 5 givenname: Martin surname: Werner fullname: Werner, Martin organization: Professorship for Big Geospatial Data Management, School of Engineering and Design, Technical University of Munich, Ottobrunn, 85521, Germany |
| BookMark | eNp9kMtu5CAQRVlkpMnrA2bHD7gHsHm0soqiTCZSpGySNSpD2cFymxbgHs3fh05HWWaFLqV7KM4FOVvigoT84mzDGVe_p80E40YwIWvujJFn5JxLtW1M14qf5CLniTGutTLnJN_SA6QAJcQFZgpribi46DHRsOR9SOjpuuR1j-kQcg0Jd7EgzbjksIw07GCs6Tivoxzn9UiiOyxv0dN_obzR3TqX0HgcE_iPd67IjwHmjNef5yV5_XP_cve3eXp-eLy7fWpcq1hpwOut11xq75SG1kkNgjst_bY1RggxAPZeCgOuV77rDQPXodZOKyENyra9JI8nro8w2X2qu6b_NkKwHxcxjRZSCW5Gy3gLQiunBjd0zLi-BTcwwQ3rBTLjK4ufWC7FnBMOXzzO7NG6nWy1bo_W7cl67dycOlg_eQiYbHah2kVftbpStwjftN8BjBWRpQ |
| Cites_doi | 10.1145/1869790.1869829 10.1109/CVPR.2018.00344 10.1109/TPAMI.2015.2439281 10.1109/ICCV.2015.67 10.1109/CVPRW.2017.151 10.1109/TCSVT.2020.3003832 10.1109/CVPR42600.2020.00251 10.1109/CVPR52688.2022.00217 10.1109/CVPRW53098.2021.00063 10.1109/CVPR46437.2021.01044 10.1080/01431161.2016.1264027 10.1109/ICCV.2017.299 10.1109/CVPR52688.2022.01712 10.1109/CVPRW50498.2020.00241 10.1109/CCCI52664.2021.9583193 10.1016/j.isprsjprs.2021.12.009 10.1016/j.rse.2024.114139 10.1007/978-3-030-01234-2_18 10.1109/CVPR52733.2024.02436 10.1109/ICCVW54120.2021.00217 |
| ContentType | Journal Article |
| Copyright | 2025 |
| Copyright_xml | – notice: 2025 |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.jag.2025.104885 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Environmental Sciences |
| ExternalDocumentID | oai_doaj_org_article_013a276c6fcf408cb3acf02180b2e08d 10_1016_j_jag_2025_104885 S1569843225005321 |
| GroupedDBID | 29J 4.4 5GY 6I. AAFTH AAHBH AALRI AAQXK AATTM AAXKI AAXUO AAYWO ABFYP ABJNI ABLST ABQEM ABQYD ABWVN ACLOT ACLVX ACRLP ACRPL ACSBN ADBBV ADMUD ADNMO ADVLN AEIPS AFJKZ AFXIZ AGQPQ AGYEJ AHEUO AIIUN AIKHN AITUG AKIFW ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP ASPBG ATOGT AVWKF AZFZN BKOJK BLECG EBS EFJIC EFKBS EJD FDB FEDTE FIRID FYGXN GROUPED_DOAJ HVGLF IMUCA KCYFY M41 O-L P-8 P-9 P2P R2- ROL SES SPC SSE SSJ ~02 AAYXX CITATION |
| ID | FETCH-LOGICAL-c360t-ad79d7157dc67a3c57a21c75d9388222faebd528acb6d4b80ac4e77c76258e533 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001598030300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1569-8432 |
| IngestDate | Mon Nov 24 19:21:14 EST 2025 Thu Nov 27 01:02:35 EST 2025 Wed Dec 10 14:25:32 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Variational autoencoder (VAE) Multi-degradation Super-resolution (SR) Unsupervised learning Remote sensing image (RSI) |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c360t-ad79d7157dc67a3c57a21c75d9388222faebd528acb6d4b80ac4e77c76258e533 |
| ORCID | 0000-0002-1920-0649 0000-0002-1647-2956 |
| OpenAccessLink | https://doaj.org/article/013a276c6fcf408cb3acf02180b2e08d |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_013a276c6fcf408cb3acf02180b2e08d crossref_primary_10_1016_j_jag_2025_104885 elsevier_sciencedirect_doi_10_1016_j_jag_2025_104885 |
| PublicationCentury | 2000 |
| PublicationDate | November 2025 2025-11-00 2025-11-01 |
| PublicationDateYYYYMMDD | 2025-11-01 |
| PublicationDate_xml | – month: 11 year: 2025 text: November 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | International journal of applied earth observation and geoinformation |
| PublicationYear | 2025 |
| Publisher | Elsevier B.V Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier |
| References | Li, B., Li, X., Zhu, H., Jin, Y., Feng, R., Zhang, Z., Chen, Z., 2024. SeD: Semantic-Aware Discriminator for Image Super-Resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Luo, Z., Huang, Y., Li, S., Wang, L., Tan, T., 2022a. Learning the degradation distribution for blind image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6063–6072. Zi, Li, Gade, Fu, Min (b33) 2024; 307 Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M., 2017. Enhanced Deep Residual Networks for Single Image Super-Resolution. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp. 136–144. Liu, Siu, Chan (b13) 2020; 31 Fernandezbeltran, Latorrecarmona, Pla (b5) 2017; 38 Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y., 2018a. Image Super-Resolution Using Very Deep Residual Channel Attention Networks. In: The European Conference on Computer Vision. pp. 294–310. Zhang, Zhou, Tong, Gao (b31) 2020 Liu, Xiao, Ma, Cui, An (b15) 2022; 184 Riegler, G., Schulter, S., Ruther, M., Bischof, H., 2015. Conditioned Regression Models for Non-blind Single Image Super-Resolution. In: IEEE International Conference on Computer Vision. pp. 522–530. Dong, Loy, He, Tang (b4) 2015; 38 Gong, Han, Lu (b6) 2017; 10 Wang, X., Xie, L., Dong, C., Shan, Y., 2021b. Real-ESRGAN: Training Real-World Blind Super-Resolution With Pure Synthetic Data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops. pp. 1905–1914. Ji, X., Cao, Y., Tai, Y., Wang, C., Li, J., Huang, F., 2020. Real-world super-resolution via kernel estimation and noise injection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 466–467. Dardour, Zaied, Radeva (b3) 2021; vol. 11605 Menon, S., Damian, A., Hu, S., Ravi, N., Rudin, C., 2020. Pulse: Self-supervised photo upsampling via latent space exploration of generative models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2437–2445. Bao, J., Chen, D., Wen, F., Li, H., Hua, G., 2017. CVAE-GAN: fine-grained image generation through asymmetric training. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2745–2754. Chira, Haralampiev, Winther, Dittadi (b2) 2022 Yan, Jiang, Luo, Wu, Dong, Mao, Wang, Liu, Yao (b24) 2024; 129 Yue, Z., Zhao, Q., Xie, J., Zhang, L., Meng, D., Wong, K.Y.K., 2022. Blind image super-resolution with elaborate degradation modeling on noise and kernel. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2128–2138. Zhang, Wang, Zhang, Xu, Wang, Ben, Zhao, Li (b29) 2022; 60 Heydari, Mehmood (b7) 2020; vol. 11400 Kingma, Welling (b9) 2013 Makhzani, Shlens, Jaitly, Goodfellow, Frey (b19) 2015 Ma, Li, Huang, Luo, He (b18) 2019 Lei, Shi (b10) 2021; 60 Wang, L., Wang, Y., Dong, X., Xu, Q., Yang, J., An, W., Guo, Y., 2021a. Unsupervised degradation representation learning for blind super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 10581–10590. Liu, Z., Siu, W., Wang, L., et al., 2021. Variational autoencoder for reference based image superresolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 516–525. Zhang, K., Zuo, W., Zhang, L., 2018b. Learning a Single Convolutional Super-Resolution Network for Multiple Degradations. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 3262–3271. Zhang, You, Shi, Gu (b30) 2025 Yang, M., Qi, J., 2021. Reference-based Image Super-Resolution by Dual-Variational AutoEncoder. In: 2021 International Conference on Communications, Computing, Cybersecurity, and Informatics. CCCI, pp. 1–5. Luo, Z., Huang, H., Yu, L., Li, Y., Fan, H., Liu, S., 2022b. Deep constrained least squares for blind image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 17642–17652. Yang, Y., Newsam, S., 2010. Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems. pp. 270–279. 10.1016/j.jag.2025.104885_b28 Dong (10.1016/j.jag.2025.104885_b4) 2015; 38 Makhzani (10.1016/j.jag.2025.104885_b19) 2015 10.1016/j.jag.2025.104885_b23 10.1016/j.jag.2025.104885_b22 10.1016/j.jag.2025.104885_b21 Ma (10.1016/j.jag.2025.104885_b18) 2019 10.1016/j.jag.2025.104885_b20 10.1016/j.jag.2025.104885_b27 10.1016/j.jag.2025.104885_b26 Fernandezbeltran (10.1016/j.jag.2025.104885_b5) 2017; 38 10.1016/j.jag.2025.104885_b25 Liu (10.1016/j.jag.2025.104885_b15) 2022; 184 10.1016/j.jag.2025.104885_b1 Zhang (10.1016/j.jag.2025.104885_b31) 2020 Heydari (10.1016/j.jag.2025.104885_b7) 2020; vol. 11400 Yan (10.1016/j.jag.2025.104885_b24) 2024; 129 Kingma (10.1016/j.jag.2025.104885_b9) 2013 10.1016/j.jag.2025.104885_b17 Lei (10.1016/j.jag.2025.104885_b10) 2021; 60 Liu (10.1016/j.jag.2025.104885_b13) 2020; 31 10.1016/j.jag.2025.104885_b12 10.1016/j.jag.2025.104885_b11 Zhang (10.1016/j.jag.2025.104885_b29) 2022; 60 10.1016/j.jag.2025.104885_b32 10.1016/j.jag.2025.104885_b16 10.1016/j.jag.2025.104885_b8 Gong (10.1016/j.jag.2025.104885_b6) 2017; 10 10.1016/j.jag.2025.104885_b14 Chira (10.1016/j.jag.2025.104885_b2) 2022 Dardour (10.1016/j.jag.2025.104885_b3) 2021; vol. 11605 Zi (10.1016/j.jag.2025.104885_b33) 2024; 307 Zhang (10.1016/j.jag.2025.104885_b30) 2025 |
| References_xml | – volume: 60 start-page: 1 year: 2022 end-page: 14 ident: b29 article-title: A multi-degradation aided method for unsupervised remote sensing image super resolution with convolution neural networks publication-title: IEEE Trans. Geosci. Remote Sens. – reference: Li, B., Li, X., Zhu, H., Jin, Y., Feng, R., Zhang, Z., Chen, Z., 2024. SeD: Semantic-Aware Discriminator for Image Super-Resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. – year: 2025 ident: b30 article-title: Uncertainty-guided perturbation for image super-resolution diffusion model – volume: 38 start-page: 295 year: 2015 end-page: 307 ident: b4 article-title: Image super-resolution using deep convolutional networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: Wang, L., Wang, Y., Dong, X., Xu, Q., Yang, J., An, W., Guo, Y., 2021a. Unsupervised degradation representation learning for blind super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 10581–10590. – reference: Bao, J., Chen, D., Wen, F., Li, H., Hua, G., 2017. CVAE-GAN: fine-grained image generation through asymmetric training. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2745–2754. – reference: Yue, Z., Zhao, Q., Xie, J., Zhang, L., Meng, D., Wong, K.Y.K., 2022. Blind image super-resolution with elaborate degradation modeling on noise and kernel. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2128–2138. – reference: Luo, Z., Huang, H., Yu, L., Li, Y., Fan, H., Liu, S., 2022b. Deep constrained least squares for blind image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 17642–17652. – reference: Luo, Z., Huang, Y., Li, S., Wang, L., Tan, T., 2022a. Learning the degradation distribution for blind image super-resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 6063–6072. – reference: Yang, Y., Newsam, S., 2010. Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems. pp. 270–279. – reference: Yang, M., Qi, J., 2021. Reference-based Image Super-Resolution by Dual-Variational AutoEncoder. In: 2021 International Conference on Communications, Computing, Cybersecurity, and Informatics. CCCI, pp. 1–5. – year: 2015 ident: b19 article-title: Adversarial autoencoders – reference: Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M., 2017. Enhanced Deep Residual Networks for Single Image Super-Resolution. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp. 136–144. – volume: vol. 11605 start-page: 593 year: 2021 end-page: 601 ident: b3 article-title: DVAE-SR: denoiser variational auto-encoder and super-resolution to counter adversarial attacks publication-title: Thirteenth International Conference on Machine Vision – volume: 10 start-page: 1865 year: 2017 end-page: 1883 ident: b6 article-title: Remote sensing image scene classification: Benchmark and state of the art publication-title: Proc. IEEE – reference: Riegler, G., Schulter, S., Ruther, M., Bischof, H., 2015. Conditioned Regression Models for Non-blind Single Image Super-Resolution. In: IEEE International Conference on Computer Vision. pp. 522–530. – reference: Ji, X., Cao, Y., Tai, Y., Wang, C., Li, J., Huang, F., 2020. Real-world super-resolution via kernel estimation and noise injection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 466–467. – reference: Menon, S., Damian, A., Hu, S., Ravi, N., Rudin, C., 2020. Pulse: Self-supervised photo upsampling via latent space exploration of generative models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 2437–2445. – volume: 38 start-page: 314 year: 2017 end-page: 354 ident: b5 article-title: Single-frame super-resolution in remote sensing: a practical overview publication-title: Int. J. Remote Sens. – reference: Liu, Z., Siu, W., Wang, L., et al., 2021. Variational autoencoder for reference based image superresolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 516–525. – reference: Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y., 2018a. Image Super-Resolution Using Very Deep Residual Channel Attention Networks. In: The European Conference on Computer Vision. pp. 294–310. – year: 2022 ident: b2 article-title: Image super-resolution with deep variational autoencoders – volume: vol. 11400 start-page: 87 year: 2020 end-page: 100 ident: b7 article-title: SRVAE: super resolution using variational autoencoders publication-title: Pattern Recognition and Tracking XXXI – reference: Wang, X., Xie, L., Dong, C., Shan, Y., 2021b. Real-ESRGAN: Training Real-World Blind Super-Resolution With Pure Synthetic Data. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops. pp. 1905–1914. – year: 2013 ident: b9 article-title: Auto-encoding variational bayes – volume: 31 start-page: 1351 year: 2020 end-page: 1365 ident: b13 article-title: Photo-realistic image super-resolution via variational autoencoders publication-title: IEEE Trans. Circuits Syst. Video Technol. – start-page: 1 year: 2020 end-page: 3 ident: b31 article-title: Image super resolution in real world using variational auto encoder publication-title: 2020 Cross Strait Radio Science & Wireless Technology Conference – volume: 184 start-page: 131 year: 2022 end-page: 147 ident: b15 article-title: Red tide detection based on high spatial resolution broad band optical satellite data publication-title: ISPRS J. Photogramm. Remote Sens. – reference: Zhang, K., Zuo, W., Zhang, L., 2018b. Learning a Single Convolutional Super-Resolution Network for Multiple Degradations. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition. pp. 3262–3271. – volume: 60 start-page: 1 year: 2021 end-page: 10 ident: b10 article-title: Hybrid-scale self-similarity exploitation for remote sensing image super-resolution publication-title: IEEE Trans. Geosci. Remote Sens. – year: 2019 ident: b18 article-title: Exploiting style and attention in real-world super-resolution – volume: 129 year: 2024 ident: b24 article-title: A multimodal data fusion model for accurate and interpretable urban land use mapping with uncertainty analysis publication-title: Int. J. Appl. Earth Obs. Geoinf. – volume: 307 year: 2024 ident: b33 article-title: Ocean eddy detection based on YOLO deep learning algorithm by synthetic aperture radar data publication-title: Remote Sens. Environ. – year: 2022 ident: 10.1016/j.jag.2025.104885_b2 – ident: 10.1016/j.jag.2025.104885_b25 doi: 10.1145/1869790.1869829 – ident: 10.1016/j.jag.2025.104885_b32 doi: 10.1109/CVPR.2018.00344 – volume: vol. 11605 start-page: 593 year: 2021 ident: 10.1016/j.jag.2025.104885_b3 article-title: DVAE-SR: denoiser variational auto-encoder and super-resolution to counter adversarial attacks – volume: 38 start-page: 295 issue: 2 year: 2015 ident: 10.1016/j.jag.2025.104885_b4 article-title: Image super-resolution using deep convolutional networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2439281 – ident: 10.1016/j.jag.2025.104885_b21 doi: 10.1109/ICCV.2015.67 – ident: 10.1016/j.jag.2025.104885_b12 doi: 10.1109/CVPRW.2017.151 – volume: 31 start-page: 1351 issue: 4 year: 2020 ident: 10.1016/j.jag.2025.104885_b13 article-title: Photo-realistic image super-resolution via variational autoencoders publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2020.3003832 – volume: 10 start-page: 1865 issue: 105 year: 2017 ident: 10.1016/j.jag.2025.104885_b6 article-title: Remote sensing image scene classification: Benchmark and state of the art publication-title: Proc. IEEE – ident: 10.1016/j.jag.2025.104885_b20 doi: 10.1109/CVPR42600.2020.00251 – start-page: 1 year: 2020 ident: 10.1016/j.jag.2025.104885_b31 article-title: Image super resolution in real world using variational auto encoder – ident: 10.1016/j.jag.2025.104885_b27 doi: 10.1109/CVPR52688.2022.00217 – ident: 10.1016/j.jag.2025.104885_b14 doi: 10.1109/CVPRW53098.2021.00063 – ident: 10.1016/j.jag.2025.104885_b22 doi: 10.1109/CVPR46437.2021.01044 – volume: 60 start-page: 1 year: 2022 ident: 10.1016/j.jag.2025.104885_b29 article-title: A multi-degradation aided method for unsupervised remote sensing image super resolution with convolution neural networks publication-title: IEEE Trans. Geosci. Remote Sens. – volume: 38 start-page: 314 issue: 1 year: 2017 ident: 10.1016/j.jag.2025.104885_b5 article-title: Single-frame super-resolution in remote sensing: a practical overview publication-title: Int. J. Remote Sens. doi: 10.1080/01431161.2016.1264027 – year: 2013 ident: 10.1016/j.jag.2025.104885_b9 – year: 2025 ident: 10.1016/j.jag.2025.104885_b30 – volume: 129 year: 2024 ident: 10.1016/j.jag.2025.104885_b24 article-title: A multimodal data fusion model for accurate and interpretable urban land use mapping with uncertainty analysis publication-title: Int. J. Appl. Earth Obs. Geoinf. – ident: 10.1016/j.jag.2025.104885_b1 doi: 10.1109/ICCV.2017.299 – ident: 10.1016/j.jag.2025.104885_b17 doi: 10.1109/CVPR52688.2022.01712 – ident: 10.1016/j.jag.2025.104885_b8 doi: 10.1109/CVPRW50498.2020.00241 – year: 2015 ident: 10.1016/j.jag.2025.104885_b19 – volume: 60 start-page: 1 year: 2021 ident: 10.1016/j.jag.2025.104885_b10 article-title: Hybrid-scale self-similarity exploitation for remote sensing image super-resolution publication-title: IEEE Trans. Geosci. Remote Sens. – ident: 10.1016/j.jag.2025.104885_b26 doi: 10.1109/CCCI52664.2021.9583193 – volume: vol. 11400 start-page: 87 year: 2020 ident: 10.1016/j.jag.2025.104885_b7 article-title: SRVAE: super resolution using variational autoencoders – volume: 184 start-page: 131 year: 2022 ident: 10.1016/j.jag.2025.104885_b15 article-title: Red tide detection based on high spatial resolution broad band optical satellite data publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2021.12.009 – volume: 307 year: 2024 ident: 10.1016/j.jag.2025.104885_b33 article-title: Ocean eddy detection based on YOLO deep learning algorithm by synthetic aperture radar data publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2024.114139 – ident: 10.1016/j.jag.2025.104885_b28 doi: 10.1007/978-3-030-01234-2_18 – ident: 10.1016/j.jag.2025.104885_b11 doi: 10.1109/CVPR52733.2024.02436 – ident: 10.1016/j.jag.2025.104885_b16 – ident: 10.1016/j.jag.2025.104885_b23 doi: 10.1109/ICCVW54120.2021.00217 – year: 2019 ident: 10.1016/j.jag.2025.104885_b18 |
| SSID | ssj0017768 |
| Score | 2.4168382 |
| Snippet | In current super-resolution (SR) research, blind SR models capable of handling multiple degradations have attracted significant attention. Inspired by... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Index Database Publisher |
| StartPage | 104885 |
| SubjectTerms | Multi-degradation Remote sensing image (RSI) Super-resolution (SR) Unsupervised learning Variational autoencoder (VAE) |
| Title | A variational autoencoder inspired unsupervised remote sensing image super resolution method with multi-degradation |
| URI | https://dx.doi.org/10.1016/j.jag.2025.104885 https://doaj.org/article/013a276c6fcf408cb3acf02180b2e08d |
| Volume | 144 |
| WOSCitedRecordID | wos001598030300001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals issn: 1569-8432 databaseCode: DOA dateStart: 20200101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: false ssIdentifier: ssj0017768 providerName: Directory of Open Access Journals |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA4iHvQguiquL3LwJBTT5tmjyooHWTyo7K3kValglXbX32-mabUX8eKxTUhKZjqPzMw3CJ1zZZzwzCZEy-Cg5CxNlMih3Ys0JaG5UF1vwOd7OZ-rxSJ_GLX6gpywCA8cD-4ymCg6k8KK0paMKGuotiUoJmIyT5QD6UtkPjhTffxAylgEx0WeKEazIZ7ZZXa96pfgGGYc4psKmiiPNFIH3D9STCNlc7uDtnsrEV_Fr9tFa76eoK0RduAEHcx-StTC1P4fbfdQe4U_gwPcX_JhvVq-A1il8w2uaoire4dXdbv6ACnRhofGB3J53EIqe_2Cq7cgYnA3HoYG1sSx1TSGe1vcZSEmDnAmYkumffR0O3u8uUv61gqJpYIsE-1k7mTKpbNCamq51FlqJXc5VWAylNobxzOlrRGOGUW0ZV5KG0QnVz6YiAdovX6v_SHCWWqs8ZTpVBPmndPUuDIYcoam3Cmhp-hiON7iIyJoFENq2WsRaFEALYpIiym6BgJ8TwTw6-5FYImiZ4niL5aYIjaQr-jtiGgfhKWq3_c--o-9j9EmLBmrFU_Q-rJZ-VO0YT-XVducdUz6BSh87b4 |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+variational+autoencoder+inspired+unsupervised+remote+sensing+image+super+resolution+method+with+multi-degradation&rft.jtitle=International+journal+of+applied+earth+observation+and+geoinformation&rft.au=Zhang%2C+Ning&rft.au=Wang%2C+Yongcheng&rft.au=Li%2C+Gang&rft.au=Xu%2C+Dongdong&rft.date=2025-11-01&rft.pub=Elsevier+B.V&rft.issn=1569-8432&rft.volume=144&rft_id=info:doi/10.1016%2Fj.jag.2025.104885&rft.externalDocID=S1569843225005321 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1569-8432&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1569-8432&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1569-8432&client=summon |