citation update, paper references DIO inclusion

Author: simon-donike

CITATION.cff

@@ -10,8 +10,14 @@ authors:
     family-names: Donike
     email: accounts@donike.net
     orcid: 'https://orcid.org/0000-0002-4440-3835'
+  - given-names: Cesar
+    family-names: Aybar
+    orcid: 'https://orcid.org/0000-0003-2745-9535'
+  - given-names: Julio
+    family-names: Contreras
+    orcid: 'https://orcid.org/0009-0001-5408-7055'
   - given-names: Luis
-    family-names: Gomez-Chova
+    family-names: Gómez-Chova
     orcid: 'https://orcid.org/0000-0003-3924-1269'
 
 repository-code: 'https://github.com/ESAOpenSR/SRGAN'

opensr_srgan/model/loss/loss.py

@@ -367,8 +367,6 @@ def _compute(weight: float, fn) -> torch.Tensor:
 
         # --- Quality metrics ---
         with torch.no_grad():
-            # sr_metric = self.normalizer.normalize(sr)
-            # hr_metric = self.normalizer.normalize(hr)
             safe_max_val = max(self.max_val, LOSS_EPS)
             sr_metric = torch.clamp(sr, 0.0, safe_max_val)
             hr_metric = torch.clamp(hr, 0.0, safe_max_val)

paper/paper.bib

@@ -2,24 +2,28 @@ @inproceedings{ledig2017photo
 	title        = {Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network},
 	author       = {Ledig, Christian and others},
 	year         = 2017,
-	booktitle    = {CVPR}
+	booktitle    = {CVPR},
+	doi          = {10.48550/arXiv.1609.04802}
 }
 @inproceedings{wang2018esrgan,
 	title        = {ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks},
 	author       = {Wang, Xintao and others},
 	year         = 2018,
-	booktitle    = {ECCV Workshops}
+	booktitle    = {ECCV Workshops},
+	doi          = {10.48550/arXiv.1809.00219}
 }
 @inproceedings{zhang2018perceptual,
 	title        = {The Unreasonable Effectiveness of Deep Features as a Perceptual Metric},
 	author       = {Zhang, Richard and others},
 	year         = 2018,
-	booktitle    = {CVPR}
+	booktitle    = {CVPR},
+	doi          = {10.48550/arXiv.1801.03924}
 }
 @misc{dong2015imagesuperresolutionusingdeep,
 	title        = {Image Super-Resolution Using Deep Convolutional Networks},
 	author       = {Chao Dong and Chen Change Loy and Kaiming He and Xiaoou Tang},
 	year         = 2015,
+	doi          = {10.48550/arXiv.1501.00092},
 	url          = {https://arxiv.org/abs/1501.00092},
 	eprint       = {1501.00092},
 	archiveprefix = {arXiv},
@@ -29,6 +33,7 @@ @misc{goodfellow2014generativeadversarialnetworks
 	title        = {Generative Adversarial Networks},
 	author       = {Ian J. Goodfellow and Jean Pouget-Abadie and Mehdi Mirza and Bing Xu and David Warde-Farley and Sherjil Ozair and Aaron Courville and Yoshua Bengio},
 	year         = 2014,
+	doi          = {10.48550/arXiv.1406.2661},
 	url          = {https://arxiv.org/abs/1406.2661},
 	eprint       = {1406.2661},
 	archiveprefix = {arXiv},
@@ -38,6 +43,7 @@ @misc{kim2016deeplyrecursiveconvolutionalnetworkimage
 	title        = {Deeply-Recursive Convolutional Network for Image Super-Resolution},
 	author       = {Jiwon Kim and Jung Kwon Lee and Kyoung Mu Lee},
 	year         = 2016,
+	doi          = {10.48550/arXiv.1511.04491},
 	url          = {https://arxiv.org/abs/1511.04491},
 	eprint       = {1511.04491},
 	archiveprefix = {arXiv},
@@ -58,6 +64,7 @@ @misc{satlassuperres
 	title        = {Zooming Out on Zooming In: Advancing Super-Resolution for Remote Sensing},
 	author       = {Piper Wolters and Favyen Bastani and Aniruddha Kembhavi},
 	year         = 2023,
+	doi          = {10.48550/arXiv.2311.18082},
 	url          = {https://arxiv.org/abs/2311.18082},
 	eprint       = {2311.18082},
 	archiveprefix = {arXiv},
@@ -78,6 +85,7 @@ @misc{su2024intriguingpropertycounterfactualexplanation
 	title        = {Intriguing Property and Counterfactual Explanation of GAN for Remote Sensing Image Generation},
 	author       = {Xingzhe Su and Wenwen Qiang and Jie Hu and Fengge Wu and Changwen Zheng and Fuchun Sun},
 	year         = 2024,
+	doi          = {10.48550/arXiv.2303.05240},
 	url          = {https://arxiv.org/abs/2303.05240},
 	eprint       = {2303.05240},
 	archiveprefix = {arXiv},
@@ -112,7 +120,8 @@ @inproceedings{p1
 	author       = {Bau, David and Zhu, Jun-Yan and Wulff, Jonas and Peebles, William and Strobelt, Hendrik and Zhou, Bolei and Torralba, Antonio},
 	year         = 2019,
 	month        = {October},
-	booktitle    = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}
+	booktitle    = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
+	doi          = {10.48550/arXiv.1910.11626}
 }
 @inproceedings{p2,
 	title        = {Improved Techniques for Training GANs},
@@ -121,14 +130,14 @@ @inproceedings{p2
 	booktitle    = {Advances in Neural Information Processing Systems},
 	publisher    = {Curran Associates, Inc.},
 	volume       = 29,
-	pages        = {},
-	url          = {https://proceedings.neurips.cc/paper_files/paper/2016/file/8a3363abe792db2d8761d6403605aeb7-Paper.pdf},
+	doi          = {10.48550/arXiv.1606.03498},
 	editor       = {D. Lee and M. Sugiyama and U. Luxburg and I. Guyon and R. Garnett}
 }
 @misc{p3,
 	title        = {GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks},
 	author       = {Christopher Bowles and Liang Chen and Ricardo Guerrero and Paul Bentley and Roger Gunn and Alexander Hammers and David Alexander Dickie and Maria Valdés Hernández and Joanna Wardlaw and Daniel Rueckert},
 	year         = 2018,
+	doi          = {10.48550/arXiv.1810.10863},
 	url          = {https://arxiv.org/abs/1810.10863},
 	eprint       = {1810.10863},
 	archiveprefix = {arXiv},
@@ -141,7 +150,7 @@ @article{agriculture
 	journal      = {Remote Sensing of Environment},
 	volume       = 236,
 	pages        = 111402,
-	doi          = {https://doi.org/10.1016/j.rse.2019.111402},
+	doi          = {10.1016/j.rse.2019.111402},
 	issn         = {0034-4257},
 	url          = {https://www.sciencedirect.com/science/article/pii/S0034425719304213},
 	keywords     = {Review, Agriculture, Remote sensing, Crop, Traits, Radiative transfer model, Inversion, Machine learning, Deep learning, Assimilation, Land use, Land cover, Yield, Precision farming, Phenotyping, Ecosystem services},
@@ -177,7 +186,8 @@ @article{disaster
 	publisher    = {Springer},
 	volume       = 87,
 	number       = 1,
-	pages        = {213--237}
+	pages        = {213--237},
+	doi          = {10.1007/s11235-024-01148-z}
 }
 @article{osrtest,
 	title        = {A Comprehensive Benchmark for Optical Remote Sensing Image Super-Resolution},
@@ -194,13 +204,15 @@ @misc{osrutils
 	title        = {OpenSR-Utils: Large-scale inference and data processing utilities for super-resolution of remote sensing imagery},
 	author       = {Donike, Simon and contributors},
 	year         = 2025,
+	doi          = {10.5281/zenodo.17599310},
 	note         = {Accessed: 2025-10-14},
 	howpublished = {\url{https://github.com/ESAOpenSR/opensr-utils}}
 }
 @misc{rcab,
 	title        = {Residual Channel Attention Generative Adversarial Network for Image Super-Resolution and Noise Reduction},
 	author       = {Jie Cai and Zibo Meng and Chiu Man Ho},
 	year         = 2020,
+	doi          = {10.48550/arXiv.2004.13674},
 	url          = {https://arxiv.org/abs/2004.13674},
 	eprint       = {2004.13674},
 	archiveprefix = {arXiv},
@@ -210,6 +222,7 @@ @misc{rrdb
 	title        = {Residual Dense Network for Image Super-Resolution},
 	author       = {Yulun Zhang and Yapeng Tian and Yu Kong and Bineng Zhong and Yun Fu},
 	year         = 2018,
+	doi          = {10.48550/arXiv.1802.08797},
 	url          = {https://arxiv.org/abs/1802.08797},
 	eprint       = {1802.08797},
 	archiveprefix = {arXiv},
@@ -219,6 +232,7 @@ @misc{lka
 	title        = {Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation},
 	author       = {Liam Chalcroft and Ruben Lourenço Pereira and Mikael Brudfors and Andrew S. Kayser and Mark D'Esposito and Cathy J. Price and Ioannis Pappas and John Ashburner},
 	year         = 2023,
+	doi          = {10.48550/arXiv.2308.07251},
 	url          = {https://arxiv.org/abs/2308.07251},
 	eprint       = {2308.07251},
 	archiveprefix = {arXiv},
@@ -228,6 +242,7 @@ @misc{patchgan
 	title        = {Patch-Based Image Inpainting with Generative Adversarial Networks},
 	author       = {Ugur Demir and Gozde Unal},
 	year         = 2018,
+	doi          = {10.48550/arXiv.1803.07422},
 	url          = {https://arxiv.org/abs/1803.07422},
 	eprint       = {1803.07422},
 	archiveprefix = {arXiv},
@@ -237,6 +252,7 @@ @misc{cyclegan
 	title        = {Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks},
 	author       = {Jun-Yan Zhu and Taesung Park and Phillip Isola and Alexei A. Efros},
 	year         = 2020,
+	doi          = {10.48550/arXiv.1703.10593},
 	url          = {https://arxiv.org/abs/1703.10593},
 	eprint       = {1703.10593},
 	archiveprefix = {arXiv},
@@ -246,6 +262,7 @@ @misc{px2px
 	title        = {Image-to-Image Translation with Conditional Adversarial Networks},
 	author       = {Phillip Isola and Jun-Yan Zhu and Tinghui Zhou and Alexei A. Efros},
 	year         = 2018,
+	doi          = {10.48550/arXiv.1611.07004},
 	url          = {https://arxiv.org/abs/1611.07004},
 	eprint       = {1611.07004},
 	archiveprefix = {arXiv},
@@ -255,6 +272,7 @@ @misc{ema
 	title        = {Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits},
 	author       = {Daniel Morales-Brotons and Thijs Vogels and Hadrien Hendrikx},
 	year         = 2024,
+	doi          = {10.48550/arXiv.2411.18704},
 	url          = {https://arxiv.org/abs/2411.18704},
 	eprint       = {2411.18704},
 	archiveprefix = {arXiv},
@@ -278,6 +296,7 @@ @misc{g1
 	title        = {Can Location Embeddings Enhance Super-Resolution of Satellite Imagery?},
 	author       = {Daniel Panangian and Ksenia Bittner},
 	year         = 2025,
+	doi          = {10.48550/arXiv.2501.15847},
 	url          = {https://arxiv.org/abs/2501.15847},
 	eprint       = {2501.15847},
 	archiveprefix = {arXiv},
@@ -287,6 +306,7 @@ @misc{allen
 	title        = {Zooming Out on Zooming In: Advancing Super-Resolution for Remote Sensing},
 	author       = {Piper Wolters and Favyen Bastani and Aniruddha Kembhavi},
 	year         = 2023,
+	doi          = {10.48550/arXiv.2311.18082},
 	url          = {https://arxiv.org/abs/2311.18082},
 	eprint       = {2311.18082},
 	archiveprefix = {arXiv},
@@ -300,8 +320,7 @@ @article{s1
 	volume       = 62,
 	number       = {},
 	pages        = {1--14},
-	doi          = {10.1109/TGRS.2023.3341437},
-	keywords     = {Remote sensing;Task analysis;Diffusion processes;Superresolution;Predictive models;Image reconstruction;Training;Diffusion probabilistic model (DPM);image super-resolution (SR);prior enhancement;remote sensing}
+	doi          = {10.1109/TGRS.2023.3341437}
 }
 @article{s2,
 	title        = {Diffusion Model with Detail Complement for Super-Resolution of Remote Sensing},
@@ -313,8 +332,7 @@ @article{s2
 	doi          = {10.3390/rs14194834},
 	issn         = {2072-4292},
 	url          = {https://www.mdpi.com/2072-4292/14/19/4834},
-	article-number = 4834,
-	abstract     = {Remote sensing super-resolution (RSSR) aims to improve remote sensing (RS) image resolution while providing finer spatial details, which is of great significance for high-quality RS image interpretation. The traditional RSSR is based on the optimization method, which pays insufficient attention to small targets and lacks the ability of model understanding and detail supplement. To alleviate the above problems, we propose the generative Diffusion Model with Detail Complement (DMDC) for RS super-resolution. Firstly, unlike traditional optimization models with insufficient image understanding, we introduce the diffusion model as a generation model into RSSR tasks and regard low-resolution images as condition information to guide image generation. Next, considering that generative models may not be able to accurately recover specific small objects and complex scenes, we propose the detail supplement task to improve the recovery ability of DMDC. Finally, the strong diversity of the diffusion model makes it possibly inappropriate in RSSR, for this purpose, we come up with joint pixel constraint loss and denoise loss to optimize the direction of inverse diffusion. The extensive qualitative and quantitative experiments demonstrate the superiority of our method in RSSR with small and dense targets. Moreover, the results from direct transfer to different datasets also prove the superior generalization ability of DMDC.}
+	article-number = 4834
 }
 @article{s3,
 	title        = {Trustworthy Super-Resolution of Multispectral Sentinel-2 Imagery With Latent Diffusion},
@@ -331,6 +349,7 @@ @misc{cgan
 	title        = {Information-theoretic stochastic contrastive conditional GAN: InfoSCC-GAN},
 	author       = {Vitaliy Kinakh and Mariia Drozdova and Guillaume Quétant and Tobias Golling and Slava Voloshynovskiy},
 	year         = 2021,
+	doi          = {10.48550/arXiv.2112.09653},
 	url          = {https://arxiv.org/abs/2112.09653},
 	eprint       = {2112.09653},
 	archiveprefix = {arXiv},