{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T15:31:51Z","timestamp":1786030311289,"version":"3.56.0"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732461","type":"print"},{"value":"9783031732478","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73247-8_5","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T12:02:20Z","timestamp":1730376140000},"page":"74-91","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":99,"title":["Pixel-Aware Stable Diffusion for\u00a0Realistic Image Super-Resolution and\u00a0Personalized Stylization"],"prefix":"10.1007","author":[{"given":"Tao","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongyuan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peiran","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuansong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Timofte, R.: Ntire 2017 challenge on single image super-resolution: dataset and study. In: CVPRW (2017)","DOI":"10.1109\/CVPRW.2017.150"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Cai, J., Zeng, H., Yong, H., Cao, Z., Zhang, L.: Toward real-world single image super-resolution: a new benchmark and a new model. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00318"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., et al.: Real-world blind super-resolution via feature matching with implicit high-resolution priors. In: ACM MM (2022)","DOI":"10.1145\/3503161.3547833"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., Liu, G., Chen, X.: Animegan: a novel lightweight gan for photo animation. In: CVPR (2020)","DOI":"10.1007\/978-981-15-5577-0_18"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Lai, Y.K., Liu, Y.J.: Cartoongan: generative adversarial networks for photo cartoonization. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00986"},{"key":"5_CR7","first-page":"2567","volume":"44","author":"K Ding","year":"2022","unstructured":"Ding, K., Ma, K., Wang, S., Simoncelli, E.P.: Image quality assessment: unifying structure and texture similarity. IEEE TPAMI 44, 2567\u20132581 (2022)","journal-title":"IEEE TPAMI"},{"key":"5_CR8","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. In: ECCV (2014)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. In: Arxiv (2015)","DOI":"10.1167\/16.12.326"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: Emu video: factorizing text-to-video generation by explicit image conditioning. In: ArXiv (2023)","DOI":"10.1007\/978-3-031-73033-7_12"},{"key":"5_CR11","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. In: NeurIPS, pp. 2672\u20132680 (2014)"},{"key":"5_CR12","unstructured":"Guo, Y., et al.: Animatediff: animate your personalized text-to-image diffusion models without specific tuning. In: ArXiv (2023)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR14","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS (2017)"},{"key":"5_CR15","unstructured":"Ho, J., et al.: Imagen video: high definition video generation with diffusion models. In: Arxiv (2022)"},{"key":"5_CR16","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS, pp. 6840\u20136851 (2020)"},{"key":"5_CR17","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: Arxiv (2021)"},{"key":"5_CR18","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"5_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"5_CR21","unstructured":"Kawar, B., Elad, M., Ermon, S., Song, J.: Denoising diffusion restoration models. In: NIPS (2022)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., Yang, F.: Musiq: multi-scale image quality transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"5_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Arxiv (2015)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Lai, W.S., Huang, J.B., Ahuja, N., Yang, M.H.: Deep laplacian pyramid networks for fast and accurate super-resolution. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.618"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"5_CR28","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"5_CR29","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.H.: Universal style transfer via feature transforms. In: NeurIPS (2017)"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Liang, J., Zeng, H., Zhang, L.: Details or artifacts: a locally discriminative learning approach to realistic image super-resolution. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00557"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Liang, J., Cao, J., Sun, G., Zhang, K., Gool, L.V., Timofte, R.: Swinir: image restoration using swin transformer. ArXiv (2021)","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Lim, B., Son, S., Kim, H., Nah, S., Lee, K.M.: Enhanced deep residual networks for single image super-resolution. In: CVPRW (2017)","DOI":"10.1109\/CVPRW.2017.151"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Lin, S., Liu, B., Li, J., Yang, X.: Common diffusion noise schedules and sample steps are flawed. In: ArXiv (2023)","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Lin, X., He, J., et al.: Diffbir: towards blind image restoration with generative diffusion prior. In: ArXiv (2023)","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"5_CR35","unstructured":"Liu, H., Xing, J., Xie, M., Li, C., Wong, T.T.: Improved diffusion-based image colorization via piggybacked models. In: ArXiv (2023)"},{"key":"5_CR36","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: Dpm-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. In: NeurIPS (2022)"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Men, Y., Yao, Y., Cui, M., Lian, Z., Xie, X.: Dct-net: domain-calibrated translation for portrait stylization. In: ACM TOG (2022)","DOI":"10.1145\/3528223.3530159"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Meng, C., Rombach, R., Gao, R., Kingma, D.P., Ermon, S., Ho, J., Salimans, T.: On distillation of guided diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01374"},{"issue":"3","key":"5_CR39","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","volume":"20","author":"A Mittal","year":"2013","unstructured":"Mittal, A., Soundararajan, R., Bovik, A.C.: Making a completely blind image quality analyzer. IEEE Signal Process. Lett. 20(3), 209\u2013212 (2013)","journal-title":"IEEE Signal Process. Lett."},{"key":"5_CR40","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"5_CR41","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. In: Arxiv (2022)"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Arxiv (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"5_CR47","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Timofte, R., Agustsson, E., Gool, L.V., Yang, M.H., Zhang, L.: Ntire 2017 challenge on single image super-resolution: methods and results. In: CVPRW, pp. 114\u2013125 (2017)","DOI":"10.1109\/CVPRW.2017.150"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Wan, Z., et al.: Bringing old photos back to life. In: CVPR (2021)","DOI":"10.1109\/CVPR42600.2020.00282"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Wang, J., Yue, Z., Zhou, S., Chan, K.C., Loy, C.C.: Exploiting diffusion prior for real-world image super-resolution. In: Arxiv (2023)","DOI":"10.1007\/s11263-024-02168-7"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Wang, X., Li, Y., Zhang, H., Shan, Y.: Towards real-world blind face restoration with generative facial prior. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Wang, X., Xie, L., Dong, C., Shan, Y.: Real-esrgan: training real-world blind super-resolution with pure synthetic data. In: ICCVW (2021)","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"Wang, X., Yu, K., Dong, C., Loy, C.C.: Recovering realistic texture in image super-resolution by deep spatial feature transform. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00070"},{"key":"5_CR54","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Esrgan: enhanced super-resolution generative adversarial networks. In: ECCVW (2018)","DOI":"10.20944\/preprints201811.0400.v1"},{"key":"5_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1007\/978-3-030-58598-3_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Wei","year":"2020","unstructured":"Wei, P., et al.: Component divide-and-conquer for real-world image super-resolution. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 101\u2013117. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_7"},{"key":"5_CR56","unstructured":"Wu, H., et al.: Q-align: Teaching LMMs for visual scoring via discrete text-defined levels. In: ArXiv (2023)"},{"key":"5_CR57","doi-asserted-by":"crossref","unstructured":"Wu, R., Yang, T., Sun, L., Zhang, Z., Li, S., Zhang, L.: SeeSR: towards semantics-aware real-world image super-resolution. In: CVPR (2023)","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"5_CR58","doi-asserted-by":"crossref","unstructured":"Yang, T., Ren, P., Xie, X., Zhang, L.: GAN prior embedded network for blind face restoration in the wild. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00073"},{"key":"5_CR59","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1007\/978-3-031-25069-9_47","volume-title":"ECCV 2022","author":"T Yang","year":"2022","unstructured":"Yang, T., Ren, P., Xie, X., Hua, X., Zhang, L.: Beyond a video frame interpolator: a space decoupled learning approach to continuous image transition. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022. LNCS, vol. 13804, pp. 738\u2013755. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25069-9_47"},{"key":"5_CR60","unstructured":"Yang, T., Ren, P., Xie, X., Zhang, L.: Synthesizing realistic image restoration training pairs: a diffusion approach. In: Arxiv (2023)"},{"key":"5_CR61","doi-asserted-by":"crossref","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00577"},{"key":"5_CR62","doi-asserted-by":"crossref","unstructured":"Yue, Z., Wang, J., Loy, C.C.: Resshift: efficient diffusion model for image super-resolution by residual shifting. In: NeurIPS (2023)","DOI":"10.1109\/TPAMI.2024.3461721"},{"key":"5_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, K., Liang, J., Gool, L.V., Timofte, R.: Designing a practical degradation model for deep blind image super-resolution. In: ICCV, pp. 4791\u20134800 (2021)","DOI":"10.1109\/ICCV48922.2021.00477"},{"key":"5_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, L., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: NeurIPS (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"5_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"5_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Inversion-based style transfer with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00978"},{"key":"5_CR67","unstructured":"Zhou, S., Chan, K.C., Li, C., Loy, C.C.: Towards robust blind face restoration with codebook lookup transformer. In: NeurIPS (2022)"},{"key":"5_CR68","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73247-8_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T15:37:32Z","timestamp":1732981052000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73247-8_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732461","9783031732478"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73247-8_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}