Hitchhiker's Guide to Super-Resolution : Introduction and Recent Advances

With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that require further research, e.g., allowing flexible upsampling, more effective loss functions, and better evaluation metrics....

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 8 vom: 10. Aug., Seite 9862-9882
1. Verfasser: Moser, Brian B (VerfasserIn)
Weitere Verfasser: Raue, Federico, Frolov, Stanislav, Palacio, Sebastian, Hees, Jorn, Dengel, Andreas
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Review Journal Article
LEADER 01000naa a22002652 4500
001 NLM355275872
003 DE-627
005 20231226064016.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2023.3243794  |2 doi 
028 5 2 |a pubmed24n1184.xml 
035 |a (DE-627)NLM355275872 
035 |a (NLM)37022895 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Moser, Brian B  |e verfasserin  |4 aut 
245 1 0 |a Hitchhiker's Guide to Super-Resolution  |b Introduction and Recent Advances 
264 1 |c 2023 
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 Completed 07.07.2023 
500 |a Date Revised 07.07.2023 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that require further research, e.g., allowing flexible upsampling, more effective loss functions, and better evaluation metrics. We review the domain of SR in light of recent advances and examine state-of-the-art models such as diffusion (DDPM) and transformer-based SR models. We critically discuss contemporary strategies used in SR and identify promising yet unexplored research directions. We complement previous surveys by incorporating the latest developments in the field, such as uncertainty-driven losses, wavelet networks, neural architecture search, novel normalization methods, and the latest evaluation techniques. We also include several visualizations for the models and methods throughout each chapter to facilitate a global understanding of the trends in the field. This review ultimately aims at helping researchers to push the boundaries of DL applied to SR 
650 4 |a Review 
650 4 |a Journal Article 
700 1 |a Raue, Federico  |e verfasserin  |4 aut 
700 1 |a Frolov, Stanislav  |e verfasserin  |4 aut 
700 1 |a Palacio, Sebastian  |e verfasserin  |4 aut 
700 1 |a Hees, Jorn  |e verfasserin  |4 aut 
700 1 |a Dengel, Andreas  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 45(2023), 8 vom: 10. Aug., Seite 9862-9882  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:45  |g year:2023  |g number:8  |g day:10  |g month:08  |g pages:9862-9882 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2023.3243794  |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 45  |j 2023  |e 8  |b 10  |c 08  |h 9862-9882