FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210571497> ?p ?o ?g. }

• W4210571497 endingPage "5040" @default.
• W4210571497 startingPage "5026" @default.
• W4210571497 abstract "Deep learning networks have recently demonstrated yielded impressive progress for multi-exposure image fusion. However, how to restore realistic texture details while correcting color distortion is still a challenging problem to be solved. To alleviate the aforementioned issues, in this paper, we propose an attention-guided global-local adversarial learning network for fusing extreme exposure images in a coarse-to-fine manner. Firstly, the coarse fusion result is generated under the guidance of attention weight maps, which acquires the essential region of interest from both sides. Secondly, we formulate an edge loss function, along with a spatial feature transform layer, for refining the fusion process. So that it can take full use of the edge information to deal with blurry edges. Moreover, by incorporating global-local learning, our method can balance pixel intensity distribution and correct the color distortion on spatially varying source images from both image/patch perspectives. Such a global-local discriminator ensures all the local patches of the fused images align with realistic normal-exposure ones. Extensive experimental results on two publicly available datasets show that our method drastically outperforms state-of-the-art methods in visual inspection and objective analysis. Furthermore, sufficient ablation experiments prove that our method has significant advantages in generating high-quality fused results with appealing details, clear targets, and faithful color. Source code 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/JinyuanLiu-CV/AGAL</uri> ." @default.
• W4210571497 created "2022-02-08" @default.
• W4210571497 creator A5006602012 @default.
• W4210571497 creator A5013834110 @default.
• W4210571497 creator A5037286379 @default.
• W4210571497 creator A5042370642 @default.
• W4210571497 date "2022-08-01" @default.
• W4210571497 modified "2023-10-16" @default.
• W4210571497 title "Attention-Guided Global-Local Adversarial Learning for Detail-Preserving Multi-Exposure Image Fusion" @default.
• W4210571497 cites W139192136 @default.
• W4210571497 cites W1985711750 @default.
• W4210571497 cites W1998393535 @default.
• W4210571497 cites W2026651590 @default.
• W4210571497 cites W2051290159 @default.
• W4210571497 cites W2065428319 @default.
• W4210571497 cites W2076205488 @default.
• W4210571497 cites W2085138920 @default.
• W4210571497 cites W2087366239 @default.
• W4210571497 cites W2103802376 @default.
• W4210571497 cites W2116702374 @default.
• W4210571497 cites W2136001449 @default.
• W4210571497 cites W2139577851 @default.
• W4210571497 cites W2163932540 @default.
• W4210571497 cites W2164847484 @default.
• W4210571497 cites W2407220925 @default.
• W4210571497 cites W2418999752 @default.
• W4210571497 cites W2545639194 @default.
• W4210571497 cites W2590560192 @default.
• W4210571497 cites W2592312604 @default.
• W4210571497 cites W2593414223 @default.
• W4210571497 cites W2746556728 @default.
• W4210571497 cites W2750638551 @default.
• W4210571497 cites W2752849939 @default.
• W4210571497 cites W2776574544 @default.
• W4210571497 cites W2783573276 @default.
• W4210571497 cites W2796014824 @default.
• W4210571497 cites W2883261402 @default.
• W4210571497 cites W2947338419 @default.
• W4210571497 cites W2948618171 @default.
• W4210571497 cites W2956718304 @default.
• W4210571497 cites W2962741876 @default.
• W4210571497 cites W2962891704 @default.
• W4210571497 cites W2963530785 @default.
• W4210571497 cites W2963685207 @default.
• W4210571497 cites W2963814095 @default.
• W4210571497 cites W2964241181 @default.
• W4210571497 cites W2964297221 @default.
• W4210571497 cites W2964362152 @default.
• W4210571497 cites W2980190282 @default.
• W4210571497 cites W2986766740 @default.
• W4210571497 cites W2995883650 @default.
• W4210571497 cites W2998012573 @default.
• W4210571497 cites W2999653953 @default.
• W4210571497 cites W3014859219 @default.
• W4210571497 cites W3015967052 @default.
• W4210571497 cites W3016539359 @default.
• W4210571497 cites W3034681889 @default.
• W4210571497 cites W3034930876 @default.
• W4210571497 cites W3035441328 @default.
• W4210571497 cites W3035503663 @default.
• W4210571497 cites W3046627924 @default.
• W4210571497 cites W3103532839 @default.
• W4210571497 cites W3109908659 @default.
• W4210571497 cites W3110670586 @default.
• W4210571497 cites W3120113457 @default.
• W4210571497 cites W3122334470 @default.
• W4210571497 cites W3126855404 @default.
• W4210571497 cites W3129817135 @default.
• W4210571497 cites W3161732772 @default.
• W4210571497 cites W3166928980 @default.
• W4210571497 cites W3169965317 @default.
• W4210571497 cites W3184581301 @default.
• W4210571497 cites W3197456663 @default.
• W4210571497 cites W4226178544 @default.
• W4210571497 doi "https://doi.org/10.1109/tcsvt.2022.3144455" @default.
• W4210571497 hasPublicationYear "2022" @default.
• W4210571497 type Work @default.
• W4210571497 citedByCount "20" @default.
• W4210571497 countsByYear W42105714972022 @default.
• W4210571497 countsByYear W42105714972023 @default.
• W4210571497 crossrefType "journal-article" @default.
• W4210571497 hasAuthorship W4210571497A5006602012 @default.
• W4210571497 hasAuthorship W4210571497A5013834110 @default.
• W4210571497 hasAuthorship W4210571497A5037286379 @default.
• W4210571497 hasAuthorship W4210571497A5042370642 @default.
• W4210571497 hasConcept C108583219 @default.
• W4210571497 hasConcept C111919701 @default.
• W4210571497 hasConcept C115961682 @default.
• W4210571497 hasConcept C126780896 @default.
• W4210571497 hasConcept C138885662 @default.
• W4210571497 hasConcept C153180895 @default.
• W4210571497 hasConcept C154945302 @default.
• W4210571497 hasConcept C160633673 @default.
• W4210571497 hasConcept C162307627 @default.
• W4210571497 hasConcept C177264268 @default.
• W4210571497 hasConcept C194257627 @default.
• W4210571497 hasConcept C199360897 @default.
• W4210571497 hasConcept C2776257435 @default.

• next