Blind Super-Resolution Via Meta-Learning and Markov Chain Monte Carlo Simulation

Blind Super-Resolution Via Meta-Learning and Markov Chain Monte Carlo Simulation

Learning based approaches have witnessed great successes in blind single image super-resolution (SISR) tasks, however, handcrafted kernel priors and learning based kernel priors are typically required. In this paper, we propose a Meta-learning and Markov Chain Monte Carlo based SISR approach to lear...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2024) vom: 17. Mai
1. Verfasser: Xia, Jingyuan (VerfasserIn)
Weitere Verfasser: Yang, Zhixiong, Li, Shengxi, Zhang, Shuanghui, Fu, Yaowen, Gunduz, Deniz, Li, Xiang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM372470289
003 DE-627
005 20240518232733.0
007 cr uuu---uuuuu
008 240518s2024 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2024.3400041  |2 doi 
028 5 2 |a pubmed24n1411.xml 
035 |a (DE-627)NLM372470289 
035 |a (NLM)38758618 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Xia, Jingyuan  |e verfasserin  |4 aut 
245 1 0 |a Blind Super-Resolution Via Meta-Learning and Markov Chain Monte Carlo Simulation 
264 1 |c 2024 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 17.05.2024 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Learning based approaches have witnessed great successes in blind single image super-resolution (SISR) tasks, however, handcrafted kernel priors and learning based kernel priors are typically required. In this paper, we propose a Meta-learning and Markov Chain Monte Carlo based SISR approach to learn kernel priors from organized randomness. In concrete, a lightweight network is adopted as kernel generator, and is optimized via learning from the MCMC simulation on random Gaussian distributions. This procedure provides an approximation for the rational blur kernel, and introduces a network-level Langevin dynamics into SISR optimization processes, which contributes to preventing bad local optimal solutions for kernel estimation. Meanwhile, a meta-learning based alternating optimization procedure is proposed to optimize the kernel generator and image restorer, respectively. In contrast to the conventional alternating minimization strategy, a meta-learning based framework is applied to learn an adaptive optimization strategy, which is less-greedy and results in better convergence performance. These two procedures are iteratively processed in a plug-and-play fashion, for the first time, realizing a learning-based but plug-and-play blind SISR solution in unsupervised inference. Extensive simulations demonstrate the superior performance and generalization ability of the proposed approach when comparing with state-of-the-arts on synthesis and real-world datasets 
650 4 |a Journal Article 
700 1 |a Yang, Zhixiong  |e verfasserin  |4 aut 
700 1 |a Li, Shengxi  |e verfasserin  |4 aut 
700 1 |a Zhang, Shuanghui  |e verfasserin  |4 aut 
700 1 |a Fu, Yaowen  |e verfasserin  |4 aut 
700 1 |a Gunduz, Deniz  |e verfasserin  |4 aut 
700 1 |a Li, Xiang  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g PP(2024) vom: 17. Mai  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:PP  |g year:2024  |g day:17  |g month:05 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2024.3400041  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2024  |b 17  |c 05