{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T23:03:16Z","timestamp":1790377396967,"version":"4.1.0"},"publisher-location":"Cham","reference-count":83,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370402","type":"print"},{"value":"9783032370419","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37041-9_22","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:32:18Z","timestamp":1788939138000},"page":"410-428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Lumina-OmniLV: A Unified Multimodal Framework for\u00a0General Low-Level Vision"],"prefix":"10.1007","author":[{"given":"Yuandong","family":"Pu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiwen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangbin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenlong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Abdelhamed, A., Lin, S., Brown, M.S.: A high-quality denoising dataset for smartphone cameras. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1692\u20131700 (2018)","DOI":"10.1109\/CVPR.2018.00182"},{"key":"22_CR2","unstructured":"Achiam, J., et al.: GPT-4 Technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Timofte, R.: Ntire 2017 challenge on single image super-resolution: Dataset and study. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 126\u2013135 (2017)","DOI":"10.1109\/CVPRW.2017.150"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Ai, Y., et al.: Dreamclear: high-capacity real-world image restoration with privacy-safe dataset curation. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024). https:\/\/openreview.net\/forum?id=6eoGVqMiIj","DOI":"10.52202\/079017-1761"},{"key":"22_CR5","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: Instructpix2pix: learning to follow image editing instructions. arXiv preprint arXiv:2211.09800 (2022)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Bychkovsky, V., Paris, S., Chan, E., Durand, F.: Learning photographic global tonal adjustment with a database of input \/ output image pairs. In: The TwentyFourth IEEE Conference on Computer Vision and Pattern Recognition (2011)","DOI":"10.1109\/CVPR.2011.5995332"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Cai, Y., Bian, H., Lin, J., Wang, H., Timofte, R., Zhang, Y.: Retinexformer: Onestage Retinex-based transformer for low-light image enhancement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12504\u201312513 (2023)","DOI":"10.1109\/ICCV51070.2023.01149"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Adversarial diffusion compression for real-world image super-resolution. arXiv preprint arXiv:2411.13383 (2024)","DOI":"10.1109\/CVPR52734.2025.02627"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., et\u00a0al.: Unireal: universal image generation and editing via learning real-world dynamics. arXiv preprint arXiv:2412.07774 (2024)","DOI":"10.1109\/CVPR52734.2025.01166"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: A comparative study of image restoration networks for general backbone network design. In: European Conference on Computer Vision, pp. 74\u201391. Springer (2024)","DOI":"10.1007\/978-3-031-73209-6_5"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Learning a low-level vision generalist via visual task prompt. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 2671\u20132680 (2024)","DOI":"10.1145\/3664647.3681621"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Chen, X., Liu, Y., Zhang, Z., Qiao, Y., Dong, C.: Hdrunet: single image HDR reconstruction with denoising and dequantization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 354\u2013363 (2021)","DOI":"10.1109\/CVPRW53098.2021.00045"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, X., Zhou, J., Qiao, Y., Dong, C.: Activating more pixels in image super-resolution transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22367\u201322377 (2023)","DOI":"10.1109\/CVPR52729.2023.02142"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhang, Z., Ren, J.S., Tian, L., Qiao, Y., Dong, C.: A new journey from SDRTV to HDRTV. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4500\u20134509 (2021)","DOI":"10.1109\/ICCV48922.2021.00446"},{"key":"22_CR16","unstructured":"Chen, X., et al.: Exploring scalable unified modeling for general low-level vision. arXiv preprint arXiv:2507.14801 (2025)"},{"key":"22_CR17","unstructured":"Chen, Z., et al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"issue":"12","key":"22_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5","volume":"67","author":"Z Chen","year":"2024","unstructured":"Chen, Z., et al.: How far are we to GPT-4v? Closing the gap to commercial multimodal models with open-source suites. Sci. China Inf. Sci. 67(12), 220101 (2024)","journal-title":"Sci. China Inf. Sci."},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"22_CR20","unstructured":"Deng, C., et\u00a0al.: Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683 (2025)"},{"issue":"2","key":"22_CR21","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2015","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295\u2013307 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Duan, Z.P., et al.: Dit4sr: taming diffusion transformer for real-world image super-resolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18948\u201318958 (2025)","DOI":"10.1109\/ICCV51701.2025.01761"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Duan, Z.P., et al.: Dit4sr: taming diffusion transformer for real-world image super-resolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18948\u201318958 (2025)","DOI":"10.1109\/ICCV51701.2025.01761"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Fu, X., Huang, J., Zeng, D., Huang, Y., Ding, X., Paisley, J.: Removing rain from single images via a deep detail network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3855\u20133863 (2017)","DOI":"10.1109\/CVPR.2017.186"},{"key":"22_CR25","unstructured":"Gao, P., et al.: Lumina-t2x: transforming text into any modality, resolution, and duration via flow-based large diffusion transformers. arXiv preprint arXiv:2405.05945 (2024)"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Guo, Y., Gao, Y., Lu, Y., Liu, R.W., He, S.: Onerestore: a universal restoration framework for composite degradation. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72655-2_15"},{"key":"22_CR28","unstructured":"Han, Z., et al.: Ace: all-round creator and editor following instructions via diffusion transformer. arXiv preprint arXiv:2410.00086 (2024)"},{"key":"22_CR29","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"22_CR31","unstructured":"Hui, M., et al.: Hq-edit: a high-quality dataset for instruction-based image editing. arXiv preprint arXiv:2404.09990 (2024)"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Zhang, Z., Xue, T., Gu, J.: Autodir: automatic all-in-one image restoration with latent diffusion. arXiv preprint arXiv:2310.10123 (2023)","DOI":"10.1007\/978-3-031-73661-2_19"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., Milanfar, P., Yang, F.: Musiq: Multi-scale image quality transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5148\u20135157 (2021)","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"22_CR34","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"22_CR35","unstructured":"Labs, B.F.: Flux (2024). https:\/\/github.com\/black-forest-labs\/flux"},{"key":"22_CR36","unstructured":"Le, D.H., et al.: One diffusion to generate them all (2024). https:\/\/arxiv.org\/abs\/2411.16318"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Li, B., Liu, X., Hu, P., Wu, Z., Lv, J., Peng, X.: All-in-one image restoration for unknown corruption. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17452\u201317462 (2022)","DOI":"10.1109\/CVPR52688.2022.01693"},{"key":"22_CR38","unstructured":"Lin, W., et al.: Pixwizard: versatile image-to-image visual assistant with open-language instructions. arXiv preprint arXiv:2409.15278 (2024)"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Lin, X., et al.: Diffbir: toward blind image restoration with generative diffusion prior. In: European Conference on Computer Vision, pp. 430\u2013448. Springer (2024)","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Lin, X., et al.: Harnessing diffusion-yielded score priors for image restoration. arXiv preprint arXiv:2507.20590 (2025)","DOI":"10.1145\/3763346"},{"key":"22_CR41","unstructured":"Liu, Y., et al.: Unifying image processing as visual prompting question answering. arXiv preprint arXiv:2310.10513 (2023)"},{"issue":"6","key":"22_CR42","doi-asserted-by":"publisher","first-page":"3064","DOI":"10.1109\/TIP.2018.2806202","volume":"27","author":"YF Liu","year":"2018","unstructured":"Liu, Y.F., Jaw, D.W., Huang, S.C., Hwang, J.N.: Desnownet: context-aware deep network for snow removal. IEEE Trans. Image Process. 27(6), 3064\u20133073 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"22_CR43","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Large-scale celebfaces attributes (celeba) dataset. Retrieved August 15(2018), 11 (2018)"},{"key":"22_CR44","unstructured":"Lu, C., Xu, L., Jia, J.: Combining sketch and tone for pencil drawing production. In: Proceedings of the Symposium on Non-photorealistic Animation and Rendering, pp. 65\u201373 (2012)"},{"key":"22_CR45","unstructured":"Luo, Z., Gustafsson, F.K., Zhao, Z., Sj\u00f6lund, J., Sch\u00f6n, T.B.: Controlling visionlanguage models for universal image restoration. arXiv preprint arXiv:2310.01018 (2023)"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Mao, C., et al.: Ace++: instruction-based image creation and editing via context-aware content filling. arXiv preprint arXiv:2501.02487 (2025)","DOI":"10.1109\/ICCVW69036.2025.00207"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: 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, vol. 38, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"22_CR50","doi-asserted-by":"crossref","unstructured":"Potlapalli, V., Zamir, S.W., Khan, S., Khan, F.: Promptir: prompting for all-in-one image restoration. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-3121"},{"key":"22_CR51","unstructured":"Ravi, N., et\u00a0al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"22_CR52","doi-asserted-by":"crossref","unstructured":"Rim, J., Lee, H., Won, J., Cho, S.: Real-world blur dataset for learning and benchmarking deblurring algorithms. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58595-2_12"},{"key":"22_CR53","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR54","doi-asserted-by":"crossref","unstructured":"Sheynin, S., et al.: Emu edit: precise image editing via recognition and generation tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8871\u20138879 (2024)","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"22_CR55","doi-asserted-by":"crossref","unstructured":"Shi, J., Xu, N., Bui, T., Dernoncourt, F., Wen, Z., Xu, C.: A benchmark and baseline for language-driven image editing. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69544-6_38"},{"key":"22_CR56","doi-asserted-by":"crossref","unstructured":"Tu, Z., et al.: Maxim: Multi-axis MLP for image processing. CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00568"},{"issue":"12","key":"22_CR57","doi-asserted-by":"publisher","first-page":"5929","DOI":"10.1007\/s11263-024-02168-7","volume":"132","author":"J Wang","year":"2024","unstructured":"Wang, J., Yue, Z., Zhou, S., Chan, K.C., Loy, C.C.: Exploiting diffusion prior for real-world image super-resolution. Int. J. Comput. Vision 132(12), 5929\u20135949 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: Underexposed photo enhancement using deep illumination estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6849\u20136857 (2019)","DOI":"10.1109\/CVPR.2019.00701"},{"key":"22_CR59","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, W., Cao, Y., Shen, C., Huang, T.: Images speak in images: a generalist painter for in-context visual learning. arXiv preprint arXiv:2212.02499 (2022)","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"22_CR60","unstructured":"Wang, X., et\u00a0al.: Emu3: next-token prediction is all you need. arXiv preprint arXiv:2409.18869 (2024)"},{"key":"22_CR61","doi-asserted-by":"crossref","unstructured":"Wang, X., Li, Y., Zhang, H., Shan, Y.: Towards real-world blind face restoration with generative facial prior. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"22_CR62","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Lavin-DIT: large vision diffusion transformer. arXiv preprint arXiv:2411.11505 (2024)","DOI":"10.1109\/CVPR52734.2025.01868"},{"key":"22_CR63","doi-asserted-by":"publisher","first-page":"8542","DOI":"10.52202\/075280-0374","volume":"36","author":"Z Wang","year":"2023","unstructured":"Wang, Z., et al.: In-context learning unlocked for diffusion models. Adv. Neural. Inf. Process. Syst. 36, 8542\u20138562 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR64","unstructured":"Wu, C., et\u00a0al.: Omnigen2: exploration to advanced multimodal generation. arXiv preprint arXiv:2506.18871 (2025)"},{"key":"22_CR65","doi-asserted-by":"publisher","first-page":"92529","DOI":"10.52202\/079017-2938","volume":"37","author":"R Wu","year":"2024","unstructured":"Wu, R., Sun, L., Ma, Z., Zhang, L.: One-step effective diffusion network for real-world image super-resolution. Adv. Neural. Inf. Process. Syst. 37, 92529\u201392553 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR66","unstructured":"Xiao, S., et al.: Omnigen: unified image generation. arXiv preprint arXiv:2409.11340 (2024)"},{"key":"22_CR67","unstructured":"Xie, E., et al.: Sana: efficient high-resolution image synthesis with linear diffusion transformer (2024). https:\/\/arxiv.org\/abs\/2410.10629"},{"key":"22_CR68","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10371\u201310381 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"22_CR69","doi-asserted-by":"crossref","unstructured":"Yang, T., Wu, R., Ren, P., Xie, X., Zhang, L.: Pixel-aware stable diffusion for realistic image super-resolution and personalized stylization. In: European Conference on Computer Vision, pp. 74\u201391. Springer (2024)","DOI":"10.1007\/978-3-031-73247-8_5"},{"key":"22_CR70","doi-asserted-by":"crossref","unstructured":"Yang, W., Wang, S., Fang, Y., Wang, Y., Liu, J.: From fidelity to perceptual quality: a semi-supervised approach for low-light image enhancement. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00313"},{"key":"22_CR71","unstructured":"Yildirim, A.B., Baday, V., Erdem, E., Erdem, A., Dundar, A.: Inst-inpaint: instructing to remove objects with diffusion models (2023)"},{"key":"22_CR72","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: 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, pp. 25669\u201325680 (2024)","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"22_CR73","doi-asserted-by":"crossref","unstructured":"Yu, Y., Zeng, Z., Hua, H., Fu, J., Luo, J.: Promptfix: you prompt and we fix the photo. In: NeurIPS (2024)","DOI":"10.52202\/079017-1263"},{"key":"22_CR74","doi-asserted-by":"crossref","unstructured":"Yue, Z., Liao, K., Loy, C.C.: Arbitrary-steps image super-resolution via diffusion inversion. arXiv preprint arXiv:2412.09013 (2024)","DOI":"10.1109\/CVPR52734.2025.02156"},{"key":"22_CR75","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., et al.: Learning enriched features for real image restoration and enhancement. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58595-2_30"},{"key":"22_CR76","doi-asserted-by":"crossref","unstructured":"Zamir, S.W., et al.: Multi-stage progressive image restoration. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"22_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, K., Mo, L., Chen, W., Sun, H., Su, Y.: Magicbrush: a manually annotated dataset for instruction-guided image editing. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-1365"},{"issue":"7","key":"22_CR78","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","volume":"26","author":"K Zhang","year":"2017","unstructured":"Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26(7), 3142\u20133155 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"22_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"22_CR80","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: Ultraedit: instruction-based fine-grained image editing at scale (2024). https:\/\/arxiv.org\/abs\/2407.05282","DOI":"10.52202\/079017-0100"},{"key":"22_CR81","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"22_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, S., Chan, K.C., Li, C., Loy, C.C.: Towards robust blind face restoration with codebook lookup transformer. In: NeurIPS (2022)","DOI":"10.52202\/068431-2218"},{"key":"22_CR83","doi-asserted-by":"crossref","unstructured":"Zhuo, L., et\u00a0al.: Lumina-next: making lumina-t2x stronger and faster with next-dit. arXiv preprint arXiv:2406.18583 (2024)","DOI":"10.52202\/079017-4172"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37041-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:32:38Z","timestamp":1788939158000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37041-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370402","9783032370419"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37041-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}