Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295934483> ?p ?o ?g. }
- W4295934483 endingPage "588" @default.
- W4295934483 startingPage "575" @default.
- W4295934483 abstract "Single image-based dehazing has achieved remarkable progress with the development of deep learning technologies. End-to-end neural networks have been proposed to learn a direct hazy-to-clear image translation to recover the clear structures and edges cues from the hazy inputs. However, the frequency domain information is explored insufficiently and lots of intermediate structure and texture related cues of current dehazing networks are ignored, which limits the performances of current approaches. To handle these limitations mentioned above, a wavelet spatial attention based multi-stream feedback network (WSAMF-Net) is proposed for effective single image dehazing. Specifically, the proposed wavelet spatial attention utilizes both frequency-domain and spatial-domain information to enhance the extracted features for better structures and edges. Meanwhile, an enhanced multi-stream based cross feature fusion strategy, including vertical and horizontal attentions, is proposed to reweight and fuse the intermediate features of each stream to acquire more meaningful aggregated features, while the weight sharing strategy is used to achieve a good trade-off between performance and parameters. Besides, feedback mechanism is also designed to provide strong reconstruction ability. Furthermore, we propose a critical real-world industrial dataset (IDS) with images captured in real-world industrial quarry scenarios for research uses. Extensive experiments on various benchmarking datasets, including both synthetic and real-world datasets, demonstrate the superiority of our WSAMF-Net over state-of-the-art single image dehazing methods. The IDS dataset will be available at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/XBSong/IDS-Datasethttps://github.com/XBSong/IDS-Dataset</uri> ." @default.
- W4295934483 created "2022-09-16" @default.
- W4295934483 creator A5009611484 @default.
- W4295934483 creator A5026243940 @default.
- W4295934483 creator A5030165903 @default.
- W4295934483 creator A5032809180 @default.
- W4295934483 creator A5036202579 @default.
- W4295934483 creator A5065065325 @default.
- W4295934483 date "2023-02-01" @default.
- W4295934483 modified "2023-10-13" @default.
- W4295934483 title "WSAMF-Net: Wavelet Spatial Attention-Based MultiStream Feedback Network for Single Image Dehazing" @default.
- W4295934483 cites W1986255332 @default.
- W4295934483 cites W2114867966 @default.
- W4295934483 cites W2116988482 @default.
- W4295934483 cites W2128254161 @default.
- W4295934483 cites W2156936307 @default.
- W4295934483 cites W2256362396 @default.
- W4295934483 cites W2467473805 @default.
- W4295934483 cites W2754480022 @default.
- W4295934483 cites W2779176852 @default.
- W4295934483 cites W2887964057 @default.
- W4295934483 cites W2891033863 @default.
- W4295934483 cites W2894289548 @default.
- W4295934483 cites W2917503345 @default.
- W4295934483 cites W2921713131 @default.
- W4295934483 cites W2945111379 @default.
- W4295934483 cites W2948606054 @default.
- W4295934483 cites W2963152299 @default.
- W4295934483 cites W2963227409 @default.
- W4295934483 cites W2963306157 @default.
- W4295934483 cites W2963495494 @default.
- W4295934483 cites W2963855133 @default.
- W4295934483 cites W2963928582 @default.
- W4295934483 cites W2964080601 @default.
- W4295934483 cites W2965130306 @default.
- W4295934483 cites W2967233860 @default.
- W4295934483 cites W2970360808 @default.
- W4295934483 cites W2970530557 @default.
- W4295934483 cites W2976715267 @default.
- W4295934483 cites W2989362930 @default.
- W4295934483 cites W2990007814 @default.
- W4295934483 cites W2998249728 @default.
- W4295934483 cites W3011856600 @default.
- W4295934483 cites W3015582066 @default.
- W4295934483 cites W3034278302 @default.
- W4295934483 cites W3034331889 @default.
- W4295934483 cites W3034725788 @default.
- W4295934483 cites W3034971973 @default.
- W4295934483 cites W3035345812 @default.
- W4295934483 cites W3035601380 @default.
- W4295934483 cites W3035631962 @default.
- W4295934483 cites W3037343293 @default.
- W4295934483 cites W3089141666 @default.
- W4295934483 cites W3107316803 @default.
- W4295934483 cites W3114126472 @default.
- W4295934483 cites W3138219084 @default.
- W4295934483 cites W3139336794 @default.
- W4295934483 cites W3163225208 @default.
- W4295934483 cites W3173269149 @default.
- W4295934483 cites W3173342677 @default.
- W4295934483 cites W3175313230 @default.
- W4295934483 cites W3175613352 @default.
- W4295934483 cites W3177127346 @default.
- W4295934483 cites W3179196239 @default.
- W4295934483 cites W3180034634 @default.
- W4295934483 cites W3193773061 @default.
- W4295934483 cites W4248646870 @default.
- W4295934483 cites W4255779515 @default.
- W4295934483 doi "https://doi.org/10.1109/tcsvt.2022.3207020" @default.
- W4295934483 hasPublicationYear "2023" @default.
- W4295934483 type Work @default.
- W4295934483 citedByCount "5" @default.
- W4295934483 countsByYear W42959344832023 @default.
- W4295934483 crossrefType "journal-article" @default.
- W4295934483 hasAuthorship W4295934483A5009611484 @default.
- W4295934483 hasAuthorship W4295934483A5026243940 @default.
- W4295934483 hasAuthorship W4295934483A5030165903 @default.
- W4295934483 hasAuthorship W4295934483A5032809180 @default.
- W4295934483 hasAuthorship W4295934483A5036202579 @default.
- W4295934483 hasAuthorship W4295934483A5065065325 @default.
- W4295934483 hasConcept C115961682 @default.
- W4295934483 hasConcept C119599485 @default.
- W4295934483 hasConcept C127413603 @default.
- W4295934483 hasConcept C134306372 @default.
- W4295934483 hasConcept C138885662 @default.
- W4295934483 hasConcept C141353440 @default.
- W4295934483 hasConcept C153180895 @default.
- W4295934483 hasConcept C154945302 @default.
- W4295934483 hasConcept C2776401178 @default.
- W4295934483 hasConcept C31972630 @default.
- W4295934483 hasConcept C33923547 @default.
- W4295934483 hasConcept C36503486 @default.
- W4295934483 hasConcept C41008148 @default.
- W4295934483 hasConcept C41895202 @default.
- W4295934483 hasConcept C47432892 @default.
- W4295934483 hasConceptScore W4295934483C115961682 @default.
- W4295934483 hasConceptScore W4295934483C119599485 @default.
- W4295934483 hasConceptScore W4295934483C127413603 @default.