{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T10:38:50Z","timestamp":1770892730245,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2022,2,20]],"date-time":"2022-02-20T00:00:00Z","timestamp":1645315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,20]],"date-time":"2022-02-20T00:00:00Z","timestamp":1645315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"the key-area research and development program of guangdong province","award":["2019B020223003"],"award-info":[{"award-number":["2019B020223003"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s00500-022-06840-3","type":"journal-article","created":{"date-parts":[[2022,2,20]],"date-time":"2022-02-20T07:02:34Z","timestamp":1645340554000},"page":"3261-3272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Boosting denoisers with reinforcement learning for image restoration"],"prefix":"10.1007","volume":"26","author":[{"given":"Jie","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Qiyuan","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8631-7305","authenticated-orcid":false,"given":"Xixuan","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jiangming","family":"Kan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,20]]},"reference":[{"key":"6840_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 conference on computer vision and pattern recognition workshops, pp 126\u2013135","DOI":"10.1109\/CVPRW.2017.150"},{"key":"6840_CR2","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.jvcir.2018.01.012","volume":"51","author":"J Anaya","year":"2018","unstructured":"Anaya J, Barbu A (2018) RENOIR-a dataset for real low-light image noise reduction. J Vis Commun Image Represent 51:144\u2013154","journal-title":"J Vis Commun Image Represent"},{"key":"6840_CR3","unstructured":"Bertsekas DP, Tsitsiklis JN (1995) Neuro-dynamic programming: an overview. In: Proceedings of 1995 34th IEEE conference on decision and control. IEEE, pp 560\u2013564"},{"key":"6840_CR4","unstructured":"Bowling M, Veloso M (2001) Rational and convergent learning in stochastic games. In: International joint conference on artificial intelligence. Lawrence Erlbaum Associates Ltd, pp 1021\u20131026"},{"key":"6840_CR5","doi-asserted-by":"crossref","unstructured":"Buades A, Coll B, Morel J-M (2005) A non-local algorithm for image denoising. In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201905). IEEE, pp 60\u201365","DOI":"10.1109\/CVPR.2005.38"},{"key":"6840_CR6","doi-asserted-by":"crossref","unstructured":"Burger HC, Schuler CJ, Harmeling S (2012) Image denoising: Can plain neural networks compete with BM3D? In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 2392\u20132399","DOI":"10.1109\/CVPR.2012.6247952"},{"key":"6840_CR7","doi-asserted-by":"crossref","unstructured":"Bu\u015foniu L, Babu\u0161ka R, De Schutter B (2010) Multi-agent reinforcement learning: an overview. In: Innovations in multi-agent systems and applications-1. Springer, pp 183\u2013221","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"6840_CR8","doi-asserted-by":"crossref","unstructured":"Cao Q, Lin L, Shi Y (2017) Attention-aware face hallucination via deep reinforcement learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 690\u2013698","DOI":"10.1109\/CVPR.2017.180"},{"key":"6840_CR9","doi-asserted-by":"crossref","unstructured":"Chen Y, Yu W, Pock T (2015) On learning optimized reaction diffusion processes for effective image restoration. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5261\u20135269","DOI":"10.1109\/CVPR.2015.7299163"},{"key":"6840_CR10","unstructured":"Chen W, Wilson J, Tyree S (2015) Compressing neural networks with the hashing trick. In: International conference on machine learning, pp 2285\u20132294"},{"key":"6840_CR11","doi-asserted-by":"crossref","unstructured":"Dabov K, Foi A, Egiazarian K (2007) Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans Image Process 16:2080\u20132095","DOI":"10.1109\/TIP.2007.901238"},{"key":"6840_CR12","doi-asserted-by":"crossref","unstructured":"Furuta R, Inoue N, Yamasaki T (2019) Pixelrl: Fully convolutional network with reinforcement learning for image processing. IEEE Trans Multimed 22(7):1704\u20131719","DOI":"10.1109\/TMM.2019.2960636"},{"key":"6840_CR13","doi-asserted-by":"crossref","unstructured":"Guo J, Chao H (2017) One-to-many network for visually pleasing compression artifacts reduction. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3038\u20133047","DOI":"10.1109\/CVPR.2017.517"},{"key":"6840_CR14","unstructured":"Guestrin C, Koller D, Parr R (2001) Solving factored POMDPs with linear value functions. In: 17th international joint conference on artificial intelligence (IJCAI-01) workshop on planning under uncertainty and incomplete information. Citeseer, pp 67\u201375"},{"key":"6840_CR15","unstructured":"Han S, Mao H, Dally WJ (2015) Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. ArXiv preprint arXiv:1510.00149"},{"key":"6840_CR16","doi-asserted-by":"crossref","unstructured":"Kim J, Lee JK, Lee KM (2016) Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1646\u20131654","DOI":"10.1109\/CVPR.2016.182"},{"key":"6840_CR17","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. ArXiv preprint arXiv:1412.6980"},{"key":"6840_CR18","unstructured":"Koller D, Parr R (2013) Policy iteration for factored MDPs. ArXiv preprint arXiv:1301.3869"},{"key":"6840_CR19","doi-asserted-by":"crossref","unstructured":"Li D, Wu H, Zhang J, Huang K (2018) A2-RL: Aesthetics aware reinforcement learning for image cropping. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8193\u20138201","DOI":"10.1109\/CVPR.2018.00855"},{"key":"6840_CR20","doi-asserted-by":"crossref","unstructured":"Li W, Feng X, An H (2020) MRI reconstruction with interpretable pixel-wise operations using reinforcement learning. In: Proceedings of the AAAI conference on artificial intelligence, pp 792\u2013799","DOI":"10.1609\/aaai.v34i01.5423"},{"key":"6840_CR21","doi-asserted-by":"crossref","unstructured":"Li Z, Zhang X (2019) Deep reinforcement learning for automatic thumbnail generation. In: International conference on multimedia modeling. Springer, pp 41\u201353","DOI":"10.1007\/978-3-030-05716-9_4"},{"key":"6840_CR22","doi-asserted-by":"crossref","unstructured":"Liao X, Li W, Xu Q (2020) Iteratively-refined interactive 3D medical image segmentation with multi-agent reinforcement learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9394\u20139402","DOI":"10.1109\/CVPR42600.2020.00941"},{"key":"6840_CR23","unstructured":"Lin L-J, Mitchell TM (1992) Memory approaches to reinforcement learning in non-Markovian domains. Carnegie-Mellon University. Department of Computer Science"},{"key":"6840_CR24","doi-asserted-by":"crossref","unstructured":"Littman ML (1994) Markov games as a framework for multi-agent reinforcement learning. In: Machine learning proceedings. Elsevier, pp 157\u2013163","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"6840_CR25","unstructured":"Littman ML (2001) Friend-or-foe Q-learning in general-sum games. In: ICML, pp 322\u2013328"},{"key":"6840_CR26","unstructured":"Lowe R, Wu YI, Tamar A (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in neural information processing systems, pp 6379\u20136390"},{"key":"6840_CR27","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/TIP.2007.911828","volume":"17","author":"J Mairal","year":"2007","unstructured":"Mairal J, Elad M, Sapiro G (2007) Sparse representation for color image restoration. IEEE Trans Image Process 17:53\u201369","journal-title":"IEEE Trans Image Process"},{"key":"6840_CR28","doi-asserted-by":"crossref","unstructured":"Park J, Lee J-Y, Yoo D, So Kweon I (2018) Distort-and-recover: color enhancement using deep reinforcement learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5928\u20135936","DOI":"10.1109\/CVPR.2018.00621"},{"key":"6840_CR29","doi-asserted-by":"crossref","unstructured":"Polikar R (2012) Ensemble learning. In: Ensemble machine learning. Springer, pp 1\u201334","DOI":"10.1007\/978-1-4419-9326-7_1"},{"key":"6840_CR30","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/0167-2789(92)90242-F","volume":"60","author":"LI Rudin","year":"1992","unstructured":"Rudin LI, Osher S, Fatemi E (1992) Nonlinear total variation based noise removal algorithms. Phys Nonlinear Phenom 60:259\u2013268","journal-title":"Phys Nonlinear Phenom"},{"key":"6840_CR31","unstructured":"Rashid T, Samvelyan M, De Witt CS (2018) QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. ArXiv preprint arXiv:1803.11485"},{"key":"6840_CR32","doi-asserted-by":"crossref","unstructured":"Singsanga S, Hattagam W, Tat EH (2010) Packet forwarding in overlay wireless sensor networks using NashQ reinforcement learning. In: 2010 6th international conference on intelligent sensors, sensor networks and information processing. IEEE, pp 85\u201390","DOI":"10.1109\/ISSNIP.2010.5706760"},{"key":"6840_CR33","doi-asserted-by":"crossref","unstructured":"Suganuma M, Liu X, Okatani T (2019) Attention-based adaptive selection of operations for image restoration in the presence of unknown combined distortions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9039\u20139048","DOI":"10.1109\/CVPR.2019.00925"},{"key":"6840_CR34","doi-asserted-by":"crossref","unstructured":"Tan M (1993) Multi-agent reinforcement learning: independent vs. cooperative agents. In: Proceedings of the 10th international conference on machine learning, pp 330\u2013337","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"6840_CR35","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1287\/opre.37.5.791","volume":"37","author":"CC White III","year":"1989","unstructured":"White CC III, Scherer WT (1989) Solution procedures for partially observed Markov decision processes. Oper Res 37:791\u2013797","journal-title":"Oper Res"},{"key":"6840_CR36","doi-asserted-by":"crossref","unstructured":"Xie C, Wu Y, Maaten LV, Yuille AL, He K (2019) Feature denoising for improving adversarial robustness. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 501\u2013509","DOI":"10.1109\/CVPR.2019.00059"},{"key":"6840_CR37","unstructured":"Yang Y, Luo R, Li M (2018) Mean field multi-agent reinforcement learning. ArXiv preprint ArXiv:1802.05438"},{"key":"6840_CR38","doi-asserted-by":"crossref","unstructured":"Yu K, Dong C, Lin L, Loy CC (2018) 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","DOI":"10.1109\/CVPR.2018.00259"},{"key":"6840_CR39","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 (2017) Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process 26:3142\u20133155","journal-title":"IEEE Trans Image Process"},{"key":"6840_CR40","unstructured":"Zhang K, Yang Z, Ba\u015far T (2019) Multi-agent reinforcement learning: a selective overview of theories and algorithms. ArXiv preprint arXiv:1911.10635"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-022-06840-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-022-06840-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-022-06840-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T12:18:49Z","timestamp":1647260329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-022-06840-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,20]]},"references-count":40,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["6840"],"URL":"https:\/\/doi.org\/10.1007\/s00500-022-06840-3","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,20]]},"assertion":[{"value":"21 January 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors declare no conflict of interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This paper does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"This paper does not contain any studies with human participants performed by any of the authors, so there is no informed consent involved.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}