{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T15:09:07Z","timestamp":1781622547158,"version":"3.54.5"},"reference-count":105,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T00:00:00Z","timestamp":1720656000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T00:00:00Z","timestamp":1720656000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG2-PhD-2022-01-033[T]"],"award-info":[{"award-number":["AISG2-PhD-2022-01-033[T]"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s11263-024-02168-7","type":"journal-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T19:01:40Z","timestamp":1720724500000},"page":"5929-5949","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":340,"title":["Exploiting Diffusion Prior for Real-World Image Super-Resolution"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7025-3626","authenticated-orcid":false,"given":"Jianyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongsheng","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangchen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelvin C. K.","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"2168_CR1","doi-asserted-by":"crossref","unstructured":"Agustsson, E., & Timofte, R. (2017). Ntire 2017 challenge on single image super-resolution: Dataset and study. In Proceedings of the IEEE\/CVF international conference on computer vision workshops (CVPR-W).","DOI":"10.1109\/CVPRW.2017.150"},{"key":"2168_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., & Fried, O. (2022). Blended diffusion for text-driven editing of natural images. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"2168_CR3","unstructured":"Balaji, Y., Nah, S., Huang, X., Vahdat, A., Song, J., Kreis, K., Aittala, M., Aila, T., Laine, S., Catanzaro, B., Karras, T., & Liu, M. Y. (2022). ediff-i: Text-to-image diffusion models with ensemble of expert denoisers. arXiv preprint arXiv:2211.01324"},{"key":"2168_CR4","doi-asserted-by":"crossref","unstructured":"Blau, Y., & Michaeli, T. (2018). The perception-distortion tradeoff. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00652"},{"key":"2168_CR5","doi-asserted-by":"crossref","unstructured":"Cai, J., Zeng, H., Yong, H., Cao, Z., & Zhang, L. (2019). Toward real-world single image super-resolution: A new benchmark and a new model. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2019.00318"},{"key":"2168_CR6","doi-asserted-by":"crossref","unstructured":"Chan, K. C., Wang, X., Xu, X., Gu, J., & Loy, C. C. (2021). GLEAN: Generative latent bank for large-factor image super-resolution. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"2168_CR7","doi-asserted-by":"crossref","unstructured":"Chan, K. C., Wang, X., Xu, X., Gu, J., & Loy, C. C. (2022). GLEAN: Generative latent bank for large-factor image super-resolution and beyond. In IEEE transactions on pattern analysis and machine intelligence (TPAMI).","DOI":"10.1109\/TPAMI.2022.3186715"},{"key":"2168_CR8","doi-asserted-by":"crossref","unstructured":"Chen, C., Shi, X., Qin, Y., Li, X., Han, X., Yang, T., & Guo, S. (2022). Real-world blind super-resolution via feature matching with implicit high-resolution priors. In Proceedings of the ACM international conference on multimedia (ACM MM).","DOI":"10.1145\/3503161.3547833"},{"key":"2168_CR9","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Guo, T., Xu, C., Deng, Y., Liu, Z., Ma, S., Xu, C., Xu, C., & Gao, W. (2021). Pre-trained image processing transformer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"2168_CR10","doi-asserted-by":"crossref","unstructured":"Choi, J., Kim, S., Jeong, Y., Gwon, Y., & Yoon, S. (2021). Ilvr: Conditioning method for denoising diffusion probabilistic models. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"2168_CR11","doi-asserted-by":"crossref","unstructured":"Choi, J., Lee, J., Shin, C., Kim, S., Kim, H., & Yoon, S. (2022). Perception prioritized training of diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.01118"},{"key":"2168_CR12","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.195"},{"key":"2168_CR13","unstructured":"Chung, H., Sim, B., Ryu, D., & Ye, J. C. (2022). Improving diffusion models for inverse problems using manifold constraints. In Proceedings of advances in neural information processing systems (NeurIPS)."},{"key":"2168_CR14","doi-asserted-by":"crossref","unstructured":"Dai, T., Cai, J., Zhang, Y., Xia, S. T., & Zhang, L. (2019). Second-order attention network for single image super-resolution. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.01132"},{"key":"2168_CR15","unstructured":"Deep-floyd. (2023). If. https:\/\/github.com\/deep-floyd\/IF"},{"key":"2168_CR16","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C. C., He, K., & Tang, X. (2014). Learning a deep convolutional network for image super-resolution. In Proceedings of the European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"2168_CR17","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. In IEEE transactions on pattern analysis and machine intelligence (TPAMI).","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"2168_CR18","doi-asserted-by":"crossref","unstructured":"Dong, C., Loy, C. C., & Tang, X. (2016). Accelerating the super-resolution convolutional neural network. In Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-319-46475-6_25"},{"key":"2168_CR19","unstructured":"Fang, G., Ma, X., & Wang, X. (2023). Structural pruning for diffusion models. In Proceedings of advances in neural information processing systems (NeurIPS)."},{"key":"2168_CR20","unstructured":"Feng, W., He, X., Fu, T. J., Jampani, V., Akula, A., Narayana, P., Basu, S., Wang, X. E., & Wang, W. Y. (2023). Training-free structured diffusion guidance for compositional text-to-image synthesis. In Proceedings of international conference on learning representations (ICLR)."},{"key":"2168_CR21","doi-asserted-by":"crossref","unstructured":"Fritsche, M., Gu, S., & Timofte, R. (2019). Frequency separation for real-world super-resolution. In Proceedings of the IEEE\/CVF international conference on computer vision workshops (ICCV-W).","DOI":"10.1109\/ICCVW.2019.00445"},{"key":"2168_CR22","doi-asserted-by":"crossref","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A. H., Chechik, G., & Cohen-Or, D. (2023). Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228","DOI":"10.1145\/3610548.3618173"},{"key":"2168_CR23","doi-asserted-by":"crossref","unstructured":"Gu, J., Shen, Y., & Zhou, B. (2020). Image processing using multi-code gan prior. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00308"},{"key":"2168_CR24","doi-asserted-by":"crossref","unstructured":"Gu, S., Chen, D., Bao, J., Wen, F., Zhang, B., Chen, D., Yuan, L., & Guo, B. (2022). Vector quantized diffusion model for text-to-image synthesis. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"2168_CR25","doi-asserted-by":"crossref","unstructured":"Gu, S., Lugmayr, A., Danelljan, M., Fritsche, M., Lamour, J., & Timofte, R. (2019). Div8k: Diverse 8k resolution image dataset. In Proceedings of the IEEE\/CVF international conference on computer vision workshops (ICCV-W).","DOI":"10.1109\/ICCVW.2019.00435"},{"key":"2168_CR26","doi-asserted-by":"crossref","unstructured":"He, X., Mo, Z., Wang, P., Liu, Y., Yang, M., & Cheng, J. (2019). Ode-inspired network design for single image super-resolution. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00183"},{"key":"2168_CR27","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., & Cohen-Or, D. (2022). Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626"},{"key":"2168_CR28","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. In Proceedings of advances in neural information processing systems (NeurIPS)."},{"key":"2168_CR29","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. In Proceedings of advances in neural information processing systems (NeurIPS) (vol.\u00a033)."},{"key":"2168_CR30","unstructured":"Ho, J., & Salimans, T. (2021). Classifier-free diffusion guidance. In Proceedings of advances in neural information processing systems (NeurIPS)."},{"key":"2168_CR31","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L. C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., & Le, Q. V. (2019). Searching for mobilenetv3. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2019.00140"},{"key":"2168_CR32","unstructured":"Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2022). Lora: Low-rank adaptation of large language models. In Proceedings of international conference on learning representations (ICLR)."},{"key":"2168_CR33","doi-asserted-by":"crossref","unstructured":"Ignatov, A., Kobyshev, N., Timofte, R., Vanhoey, K., & Van\u00a0Gool, L. (2017). Dslr-quality photos on mobile devices with deep convolutional networks. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2017.355"},{"key":"2168_CR34","doi-asserted-by":"crossref","unstructured":"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 international conference on computer vision workshops (CVPR-W).","DOI":"10.1109\/CVPRW50498.2020.00241"},{"key":"2168_CR35","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Chan, K. C., Wang, X., Loy, C. C., & Liu, Z. (2021). Robust reference-based super-resolution via c2-matching. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00214"},{"key":"2168_CR36","unstructured":"Jim\u00e9nez, \u00c1. B. (2023). Mixture of diffusers for scene composition and high resolution image generation. arXiv preprint arXiv:2302.02412"},{"key":"2168_CR37","unstructured":"Karras, T., Aittala, M., Aila, T., & Laine, S. (2022). Elucidating the design space of diffusion-based generative models. In Proceedings of advances in neural information processing systems (NeurIPS)."},{"key":"2168_CR38","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2168_CR39","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., & Yang, F. (2021). Musiq: Multi-scale image quality transformer. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"2168_CR40","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"2168_CR41","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Husz\u00e1r, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., & Shi, W. (2017). Photo-realistic single image super-resolution using a generative adversarial network. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.19"},{"key":"2168_CR42","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.neucom.2022.02.082","volume":"6","author":"H Li","year":"2022","unstructured":"Li, H., Yang, Y., Chang, M., Chen, S., Feng, H., Xu, Z., Li, Q., & Chen, Y. (2022). SRDiff: Single image super-resolution with diffusion probabilistic models. Neurocomputing, 6, 66.","journal-title":"Neurocomputing"},{"key":"2168_CR43","doi-asserted-by":"crossref","unstructured":"Liang, J., Cao, J., Sun, G., Zhang, K., Van\u00a0Gool, L., & Timofte, R. (2021). SwinIR: Image restoration using swin transformer. In Proceedings of the IEEE\/CVF international conference on computer vision workshops (ICCV-W).","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"2168_CR44","doi-asserted-by":"crossref","unstructured":"Liang, J., Zeng, H., & Zhang, L. (2022). Efficient and degradation-adaptive network for real-world image super-resolution. In Proceedings of the European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-031-19797-0_33"},{"key":"2168_CR45","unstructured":"Lin, X., He, J., Chen, Z., Lyu, Z., Fei, B., Dai, B., Ouyang, W., Qiao, Y., & Dong, C. (2023). Diffbir: Towards blind image restoration with generative diffusion prior. arXiv preprint arXiv:2308.15070"},{"key":"2168_CR46","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2168_CR47","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., & Zhu, J. (2022). Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps. In Proceedings of advances in neural information processing systems (NeurIPS)."},{"key":"2168_CR48","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., & Zhao, H. (2023). Latent consistency models: Synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378"},{"key":"2168_CR49","doi-asserted-by":"crossref","unstructured":"Maeda, S. (2020). Unpaired image super-resolution using pseudo-supervision. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00037"},{"key":"2168_CR50","unstructured":"Meng, X., & Kabashima, Y. (2022). Diffusion model based posterior sampling for noisy linear inverse problems. arXiv preprint arXiv:2211.12343"},{"key":"2168_CR51","doi-asserted-by":"crossref","unstructured":"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 (CVPR).","DOI":"10.1109\/CVPR42600.2020.00251"},{"key":"2168_CR52","unstructured":"Molad, E., Horwitz, E., Valevski, D., Acha, A. R., Matias, Y., Pritch, Y., Leviathan, Y., & Hoshen, Y. (2023). Dreamix: Video diffusion models are general video editors. arXiv preprint arXiv:2302.01329"},{"key":"2168_CR53","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Xie, L., Wu, Y., Zhang, J., Qi, Z., & Shan, Y. (2024). T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. In Proceedings of the AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"2168_CR54","unstructured":"Nichol, A. Q., Dhariwal, P., Ramesh, A., Shyam, P., Mishkin, P., Mcgrew, B., Sutskever, I., & Chen, M. (2022). Glide: Towards photorealistic image generation and editing with text-guided diffusion models. In Proceedings of international conference on machine learning (ICML)."},{"key":"2168_CR55","unstructured":"Oord, Avd., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748"},{"key":"2168_CR56","doi-asserted-by":"crossref","unstructured":"Pan, X., Zhan, X., Dai, B., Lin, D., Loy, C. C., & Luo, P. (2021). Exploiting deep generative prior for versatile image restoration and manipulation. In IEEE transactions on pattern analysis and machine intelligence (TPAMI).","DOI":"10.1109\/TPAMI.2021.3115428"},{"key":"2168_CR57","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., & Rombach, R. (2023). Sdxl: Improving latent diffusion models for high-resolution image synthesis. In Proceedings of international conference on learning representations (ICLR)."},{"key":"2168_CR58","doi-asserted-by":"crossref","unstructured":"Qi, C., Cun, X., Zhang, Y., Lei, C., Wang, X., Shan, Y., & Chen, Q. (2023). Fatezero: Fusing attentions for zero-shot text-based video editing. arXiv preprint arXiv:2303.09535","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"2168_CR59","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022). Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125"},{"key":"2168_CR60","unstructured":"Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021). Zero-shot text-to-image generation. In Proceedings of international conference on machine learning (ICML)."},{"key":"2168_CR61","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2168_CR62","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention (MICCAI) (pp. 234\u2013241). Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2168_CR63","unstructured":"Sahak, H., Watson, D., Saharia, C., & Fleet, D. (2023). Denoising diffusion probabilistic models for robust image super-resolution in the wild. arXiv preprint arXiv:2302.07864"},{"key":"2168_CR64","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E. L., Ghasemipour, K., Gontijo Lopes, R., Karagol Ayan, B., Salimans, T., & Ho, J. (2022a). Photorealistic text-to-image diffusion models with deep language understanding. In Proceedings of advances in neural information processing systems (NeurIPS).","DOI":"10.1145\/3528233.3530757"},{"key":"2168_CR65","doi-asserted-by":"crossref","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D. J., & Norouzi, M. (2022b). Image super-resolution via iterative refinement. In IEEE transactions on pattern analysis and machine intelligence (TPAMI).","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"2168_CR66","doi-asserted-by":"crossref","unstructured":"Sajjadi, M. S., Scholkopf, B., & Hirsch, M. (2017). Enhancenet: Single image super-resolution through automated texture synthesis. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.481"},{"key":"2168_CR67","unstructured":"Salimans, T., & Ho, J. (2021). Progressive distillation for fast sampling of diffusion models. In Proceedings of international conference on learning representations (ICLR)."},{"key":"2168_CR68","doi-asserted-by":"crossref","unstructured":"Sauer, A., Lorenz, D., Blattmann, A., & Rombach, R. (2023). Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"2168_CR69","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., & Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of international conference on machine learning (ICML)."},{"key":"2168_CR70","unstructured":"Song, J., Meng, C., & Ermon, S. (2020). Denoising diffusion implicit models. In Proceedings of international conference on learning representations (ICLR)."},{"key":"2168_CR71","unstructured":"Song, J., Vahdat, A., Mardani, M., & Kautz, J. (2023a). Pseudoinverse-guided diffusion models for inverse problems. In Proceedings of international conference on learning representations (ICLR)."},{"key":"2168_CR72","unstructured":"Song, Y., Dhariwal, P., Chen, M., & Sutskever, I. (2023b). Consistency models. arXiv preprint arXiv:2303.01469"},{"key":"2168_CR73","first-page":"66","volume":"6","author":"EL Thorndike","year":"1920","unstructured":"Thorndike, E. L., et al. (1920). A constant error in psychological ratings. Journal of Applied Psychology, 6, 66.","journal-title":"Journal of Applied Psychology"},{"key":"2168_CR74","doi-asserted-by":"crossref","unstructured":"Timofte, R., Agustsson, E., Van\u00a0Gool, L., Yang, M. H., & Zhang, L. (2017). Ntire 2017 challenge on single image super-resolution: Methods and results. In Proceedings of the IEEE\/CVF international conference on computer vision workshops (CVPR-W).","DOI":"10.1109\/CVPRW.2017.150"},{"key":"2168_CR75","doi-asserted-by":"crossref","unstructured":"Wan, Z., Zhang, B., Chen, D., Zhang, P., Chen, D., Liao, J., & Wen, F. (2020). Bringing old photos back to life. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00282"},{"key":"2168_CR76","doi-asserted-by":"crossref","unstructured":"Wang, J., Chan, K. C., & Loy, C. C. (2023). Exploring clip for assessing the look and feel of images. In Proceedings of the AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"2168_CR77","doi-asserted-by":"crossref","unstructured":"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 (CVPR).","DOI":"10.1109\/CVPR46437.2021.01044"},{"key":"2168_CR78","doi-asserted-by":"crossref","unstructured":"Wang, X., Li, Y., Zhang, H., & Shan, Y. (2021b). Towards real-world blind face restoration with generative facial prior. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"2168_CR79","doi-asserted-by":"crossref","unstructured":"Wang, X., Xie, L., Dong, C., & Shan, Y. (2021c). Real-esrgan: Training real-world blind super-resolution with pure synthetic data. In Proceedings of the IEEE\/CVF international conference on computer vision workshops (ICCV-W).","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"2168_CR80","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, K., Dong, C., & Loy, C. C. (2018a). Recovering realistic texture in image super-resolution by deep spatial feature transform. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00070"},{"key":"2168_CR81","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., & Loy, C. C. (2018b). Esrgan: Enhanced super-resolution generative adversarial networks. In Proceedings of the European conference on computer vision workshops (ECCV-W).","DOI":"10.1007\/978-3-030-11021-5_5"},{"key":"2168_CR82","unstructured":"Wang, Y., Yu, J., & Zhang, J. (2022). Zero-shot image restoration using denoising diffusion null-space model. In Proceedings of international conference on learning representations (ICLR)."},{"key":"2168_CR83","doi-asserted-by":"crossref","unstructured":"Wei, P., Xie, Z., Lu, H., Zhan, Z., Ye, Q., Zuo, W., & Lin, L. (2020). Component divide-and-conquer for real-world image super-resolution. In Proceedings of the European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-58598-3_7"},{"key":"2168_CR84","doi-asserted-by":"crossref","unstructured":"Wei, Y., Gu, S., Li, Y., Timofte, R., & Jin, L., Song, H. (2021). Unsupervised real-world image super resolution via domain-distance aware training. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.01318"},{"key":"2168_CR85","doi-asserted-by":"crossref","unstructured":"Wu, J. Z., Ge, Y., Wang, X., Lei, S. W., Gu, Y., Hsu, W., Shan, Y., Qie, X., & Shou, M. Z. (2022). Tune-A-Video: One-shot tuning of image diffusion models for text-to-video generation. arXiv preprint arXiv:2212.11565","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"2168_CR86","doi-asserted-by":"crossref","unstructured":"Xu, X., Ma, Y., & Sun, W. (2019). Towards real scene super-resolution with raw images. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00182"},{"key":"2168_CR87","doi-asserted-by":"crossref","unstructured":"Xu, X., Sun, D., Pan, J., Zhang, Y., Pfister, H., & Yang, M. H. (2017). Learning to super-resolve blurry face and text images. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.36"},{"key":"2168_CR88","doi-asserted-by":"crossref","unstructured":"Yang, F., Yang, H., Fu, J., Lu, H., & Guo, B. (2020). Learning texture transformer network for image super-resolution. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"2168_CR89","unstructured":"Yang, S., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2021a). Score-based generative modeling through stochastic differential equations. In Proceedings of international conference on learning representations (ICLR)."},{"key":"2168_CR90","doi-asserted-by":"crossref","unstructured":"Yang, T., Ren, P., Xie, X., & Zhang, L. (2021b). Gan prior embedded network for blind face restoration in the wild. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR46437.2021.00073"},{"key":"2168_CR91","doi-asserted-by":"crossref","unstructured":"Yu, F., Gu, J., Li, Z., Hu, J., Kong, X., Wang, X., He, J., Qiao, Y., & Dong, C. (2024). Scaling up to excellence: Practicing model scaling for photo-realistic image restoration in the wild. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"2168_CR92","doi-asserted-by":"crossref","unstructured":"Yu, K., Dong, C., Lin, L., & Loy, C. C. (2018). Crafting a toolchain for image restoration by deep reinforcement learning. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00259"},{"key":"2168_CR93","unstructured":"Yue, Z., & Loy, C. C. (2022). Difface: Blind face restoration with diffused error contraction. arXiv preprint arXiv:2212.06512"},{"key":"2168_CR94","doi-asserted-by":"crossref","unstructured":"Yue, Z., Wang, J., & Loy, C. C. (2023). Resshift: Efficient diffusion model for image super-resolution by residual shifting. In Proceedings of advances in neural information processing systems (NeurIPS).","DOI":"10.1109\/TPAMI.2024.3461721"},{"key":"2168_CR95","unstructured":"Zhang, J., Lu, S., Zhan, F., & Yu, Y. (2021a). Blind image super-resolution via contrastive representation learning. arXiv preprint arXiv:2107.00708"},{"key":"2168_CR96","doi-asserted-by":"crossref","unstructured":"Zhang, K., Liang, J., Van\u00a0Gool, L., & Timofte, R. (2021b). Designing a practical degradation model for deep blind image super-resolution. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV48922.2021.00475"},{"key":"2168_CR97","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"2168_CR98","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018a). The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00068"},{"key":"2168_CR99","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., & Fu, Y. (2018b). Image super-resolution using very deep residual channel attention networks. In Proceedings of the European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"2168_CR100","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Wang, Z., Lin, Z., & Qi, H. (2019). Image super-resolution by neural texture transfer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2019.00817"},{"key":"2168_CR101","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Su, Y. C., Chu, C. T., Li, Y., Renn, M., Zhu, Y., Chen, C., & Jia, X. (2022). Rethinking deep face restoration. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00750"},{"key":"2168_CR102","doi-asserted-by":"crossref","unstructured":"Zheng, H., Ji, M., Wang, H., Liu, Y., & Fang, L. (2018). Crossnet: An end-to-end reference-based super resolution network using cross-scale warping. In Proceedings of the European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01231-1_6"},{"key":"2168_CR103","unstructured":"Zhou, S., Chan, K. C., Li, C., & Loy, C. C. (2022). Towards robust blind face restoration with codebook lookup transformer. In Proceedings of advances in neural information processing systems (NeurIPS)."},{"key":"2168_CR104","unstructured":"Zhou, S., Zhang, J., Zuo, W., & Loy, C. C. (2020). Cross-scale internal graph neural network for image super-resolution. In Proceedings of advances in neural information processing systems (NeurIPS)."},{"key":"2168_CR105","doi-asserted-by":"crossref","unstructured":"Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE\/CVF international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02168-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02168-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02168-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T10:24:13Z","timestamp":1731666253000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02168-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,11]]},"references-count":105,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["2168"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02168-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,11]]},"assertion":[{"value":"5 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}