{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:06:16Z","timestamp":1789538776190,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376237","type":"print"},{"value":"9783032376244","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\/978-3-032-37624-4_21","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:50:44Z","timestamp":1789537844000},"page":"335-352","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Physics Meets Perception: A Reinforcement Learning Framework for\u00a0Unpaired Real-World Image Dehazing"],"prefix":"10.1007","author":[{"given":"Yunwei","family":"Lan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhigao","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Menglin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Ancuti, C.O., Ancuti, C., Timofte, R., et\u00a0al.: O-HAZE: a dehazing benchmark with real hazy and haze-free outdoor images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 754\u2013762 (2018)","DOI":"10.1109\/CVPRW.2018.00119"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Ancuti, C., Ancuti, C.O., Timofte, R., et\u00a0al.: I-HAZE: a dehazing benchmark with real hazy and haze-free indoor images. In: Advanced Concepts for Intelligent Vision Systems, pp. 620\u2013631. Springer (2018)","DOI":"10.1007\/978-3-030-01449-0_52"},{"key":"21_CR3","unstructured":"Bai, S., Chen, K., Liu, X.: Qwen2.5-VL technical report (2025). arXiv preprint arXiv:2502.13923"},{"key":"21_CR4","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1109\/TIP.2024.3354108","volume":"33","author":"Z Chen","year":"2024","unstructured":"Chen, Z., He, Z., Lu, Z.M.: DEA-Net: single image dehazing based on detail-enhanced convolution and content-guided attention. IEEE Trans. Image Process. 33, 1002\u20131015 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Engin, D., Gen\u00e7, A., Kemal\u00a0Ekenel, H.: Cycle-Dehaze: enhanced CycleGAN for single image dehazing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 825\u2013833 (2018)","DOI":"10.1109\/CVPRW.2018.00127"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Fang, W., Fan, J., Zheng, Y.: Guided real image dehazing using YCbCr color space. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 2906\u20132914 (2025)","DOI":"10.1609\/aaai.v39i3.32297"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Fattal, R.: Dehazing using color-lines. ACM Trans. Graph. (TOG) 34(1), 1\u201314 (2014)","DOI":"10.1145\/2651362"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Feng, Y., Ma, L., Meng, X., et al.: Advancing real-world image dehazing: perspective, modules, and training. IEEE Trans. Pattern Anal. Mach. Intell. 46(12), 9303\u20139320 (2024)","DOI":"10.1109\/TPAMI.2024.3416731"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, S., Liu, Z., et\u00a0al.: Iterative predictor-critic code decoding for real-world image dehazing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312709 (2025)","DOI":"10.1109\/CVPR52734.2025.01185"},{"issue":"7","key":"21_CR10","doi-asserted-by":"publisher","first-page":"1704","DOI":"10.1109\/TMM.2019.2960636","volume":"22","author":"R Furuta","year":"2019","unstructured":"Furuta, R., Inoue, N., Yamasaki, T.: PixelRL: fully convolutional network with reinforcement learning for image processing. IEEE Trans. Multimedia 22(7), 1704\u20131719 (2019)","journal-title":"IEEE Trans. Multimedia"},{"issue":"11","key":"21_CR11","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"issue":"12","key":"21_CR12","first-page":"2341","volume":"33","author":"K He","year":"2010","unstructured":"He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341\u20132353 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Hu, T., et al.: Boosting HDR image reconstruction via semantic knowledge transfer. IEEE Trans. Image Process. 35, 1910\u20131922 (2026)","DOI":"10.1109\/TIP.2026.3652360"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Hu, T., et al.: Ghost-free HDR imaging via latent low-frequency priors and deformable attention alignment. IEEE Trans. Image Process. 35, 2684\u20132698 (2026)","DOI":"10.1109\/TIP.2026.3671656"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Hu, T., Yan, Q., Qi, Y., Zhang, Y.: Generating content for HDR deghosting from frequency view. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 25732\u201325741 (2024)","DOI":"10.1109\/CVPR52733.2024.02431"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Ke, J., Wang, Q., Wang, Y., et\u00a0al.: 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":"21_CR17","doi-asserted-by":"crossref","unstructured":"Lan, Y., Cui, Z., Liu, C.: Exploiting diffusion prior for real-world image dehazing with unpaired training. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 4455\u20134463. (2025)","DOI":"10.1609\/aaai.v39i4.32469"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Lan, Y., et al.: When schrodinger bridge meets real-world image dehazing with unpaired training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8756\u20138765 (2025)","DOI":"10.1109\/ICCV51701.2025.00819"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Li, B., Peng, X., Wang, Z.: AOD-Net: all-in-one dehazing network. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4770\u20134778 (2017)","DOI":"10.1109\/ICCV.2017.511"},{"issue":"1","key":"21_CR20","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1109\/TIP.2018.2867951","volume":"28","author":"B Li","year":"2018","unstructured":"Li, B., Ren, W., Fu, D., et al.: Benchmarking single-image dehazing and beyond. IEEE Trans. Image Process. 28(1), 492\u2013505 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR21","doi-asserted-by":"publisher","first-page":"1754","DOI":"10.1007\/s11263-021-01431-5","volume":"129","author":"B Li","year":"2021","unstructured":"Li, B., Gou, Y., Gu, S., et al.: You only look yourself: unsupervised and untrained single image dehazing neural network. Int. J. Comput. Vision 129, 1754\u20131767 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"21_CR22","unstructured":"Liu, A., Feng, B., Xue, B.: DeepSeek-V3 technical report (2025). arXiv preprint arXiv:2412.19437"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C., Qi, L., Pan, J.: Frequency domain-based diffusion model for unpaired image dehazing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7538\u20137547 (2025)","DOI":"10.1109\/ICCV51701.2025.00707"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Liu, F., Xu, J., Hu, X.: Real-world adverse weather image restoration via dual-level reinforcement learning with high-quality cold start. In: Advances in Neural Information Processing Systems, vol. 38, pp. 112525\u2013112599 (2025)","DOI":"10.52202\/085713-3759"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, G., Liang, J., et\u00a0al.: Flow-GRPO: training flow matching models via online RL. In: Advances in Neural Information Processing Systems, vol.\u00a038, pp. 40783\u201340818 (2025)","DOI":"10.52202\/085713-1362"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Mittal, A., Soundararajan, R., Bovik, A.C.: Making a \u201ccompletely blind\u201d image quality analyzer. IEEE Sig. Process. Lett. 20(3), 209\u2013212 (2012)","DOI":"10.1109\/LSP.2012.2227726"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Nayar, S.K., Narasimhan, S.G.: Vision in bad weather. In: Proceedings of the IEEE International Conference on Computer Vision, vol. 2, pp. 820\u2013827. IEEE (1999)","DOI":"10.1109\/ICCV.1999.790306"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Park, T., Efros, A.A., Zhang, R.: Contrastive learning for unpaired image-to-image translation. In: Computer Vision - ECCV, pp. 319\u2013345. Springer (2020)","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Qiu, Y., Zhang, K., Wang, C.: MB-TaylorFormer: multi-branch efficient transformer expanded by Taylor formula for image dehazing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12802\u201312813 (2023)","DOI":"10.1109\/ICCV51070.2023.01176"},{"key":"21_CR30","unstructured":"Radford, A., Kim, J.W., Hallacy, C.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention - MICCAI, pp. 234\u2013241 Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"21_CR32","unstructured":"Schulman, J., Wolski, F., Dhariwal, P.: Proximal policy optimization algorithms, (2017). arXiv preprint arXiv:1707.06347"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Shao, Y., Li, L., Ren, W.: Domain adaptation for image dehazing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2808\u20132817 (2020)","DOI":"10.1109\/CVPR42600.2020.00288"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Shin, J., Chung, S., Yang, Y.: HazeFlow: revisit haze physical model as ODE and non-homogeneous haze generation for real-world dehazing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6263\u20136272 (2025)","DOI":"10.1109\/ICCV51701.2025.00591"},{"key":"21_CR35","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1109\/TIP.2023.3256763","volume":"32","author":"Y Song","year":"2023","unstructured":"Song, Y., He, Z., Qian, H., et al.: Vision transformers for single image dehazing. IEEE Trans. Image Process. 32, 1927\u20131941 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Wang, J., Chan, K.C., Loy, C.C.: Exploring CLIP for assessing the look and feel of images. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 2555\u20132563 (2023)","DOI":"10.1609\/aaai.v37i2.25353"},{"issue":"1","key":"21_CR37","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/TCSVT.2025.3596024","volume":"36","author":"N Wang","year":"2026","unstructured":"Wang, N., Cui, Z., Su, Y., et al.: Weakly supervised image dehazing via physics-based decomposition. IEEE Trans. Circuits Syst. Video Technol. 36(1), 637\u2013652 (2026)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"21_CR38","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.1109\/TIP.2024.3362153","volume":"33","author":"Y Wang","year":"2024","unstructured":"Wang, Y., Yan, X., Wang, F.L., et al.: UCL-Dehaze: towards real-world image dehazing via unsupervised contrastive learning. IEEE Trans. Image Process. 33, 1361\u20131374 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR39","doi-asserted-by":"crossref","unstructured":"Wu, R., Sun, L., Zhang, Z.: DP2O-SR: direct perceptual preference optimization for real-world image super-resolution. In: Advances in Neural Information Processing Systems, vol. 38, pp. 172015\u2013172041 (2025)","DOI":"10.52202\/085713-5723"},{"key":"21_CR40","unstructured":"Xu, H., Liu, Y., Jiang, B.: IRPO: boosting image restoration via post-training GRPO (2025). arXiv preprint arXiv:2512.00814"},{"key":"21_CR41","unstructured":"Xu, X., Chu, R., Wang, J.: Enhancing diffusion-based restoration models via difficulty-adaptive reinforcement learning with IQA reward (2025). arXiv preprint arXiv:2511.01645"},{"key":"21_CR42","unstructured":"Xue, Z., Wu, J., Gao, Y.: DanceGRPO: unleashing GRPO on visual generation (2025). arXiv preprint arXiv:2505.07818"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Yang, S., Wu, T., Shi, S.: MANIQA: multi-dimension attention network for no-reference image quality assessment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1191\u20131200 (2022)","DOI":"10.1109\/CVPRW56347.2022.00126"},{"issue":"5","key":"21_CR44","doi-asserted-by":"publisher","first-page":"1557","DOI":"10.1007\/s11263-023-01940-5","volume":"132","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Wang, C., Guo, X., et al.: Robust unpaired image dehazing via density and depth decomposition. Int. J. Comput. Vision 132(5), 1557\u20131577 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"21_CR45","doi-asserted-by":"crossref","unstructured":"Yang, Y., Wang, C., Liu, R.: Self-augmented unpaired image dehazing via density and depth decomposition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2037\u20132046 (2022)","DOI":"10.1109\/CVPR52688.2022.00208"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Yu, K., Dong, C., Lin, L.: Crafting a toolchain for image restoration by deep reinforcement learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2443\u20132452 (2018)","DOI":"10.1109\/CVPR.2018.00259"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, H., Patel, V.M.: Densely connected pyramid dehazing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3194\u20133203 (2018)","DOI":"10.1109\/CVPR.2018.00337"},{"issue":"10","key":"21_CR48","doi-asserted-by":"publisher","first-page":"4270","DOI":"10.1109\/TIP.2014.2346028","volume":"23","author":"L Zhang","year":"2014","unstructured":"Zhang, L., Shen, Y., Li, H.: VSI: a visual saliency-induced index for perceptual image quality assessment. IEEE Trans. Image Process. 23(10), 4270\u20134281 (2014)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"21_CR50","doi-asserted-by":"publisher","first-page":"3391","DOI":"10.1109\/TIP.2021.3060873","volume":"30","author":"S Zhao","year":"2021","unstructured":"Zhao, S., Zhang, L., Shen, Y., et al.: RefineDNet: a weakly supervised refinement framework for single image dehazing. IEEE Trans. Image Process. 30, 3391\u20133404 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR51","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhan, J., He, S.: Curricular contrastive regularization for physics-aware single image dehazing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5785\u20135794 (2023)","DOI":"10.1109\/CVPR52729.2023.00560"},{"key":"21_CR52","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., Zhao, H., Puig, X., et al.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vision 127, 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vision"},{"issue":"11","key":"21_CR53","doi-asserted-by":"publisher","first-page":"3522","DOI":"10.1109\/TIP.2015.2446191","volume":"24","author":"Q Zhu","year":"2015","unstructured":"Zhu, Q., Mai, J., Shao, L.: A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Process. 24(11), 3522\u20133533 (2015)","journal-title":"IEEE Trans. Image Process."}],"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\/978-3-032-37624-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:51:08Z","timestamp":1789537868000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37624-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376237","9783032376244"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37624-4_21","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":"17 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"}}]}}