Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321792645> ?p ?o ?g. }
- W4321792645 endingPage "103794" @default.
- W4321792645 startingPage "103794" @default.
- W4321792645 abstract "This paper presents a bilateral attention based generative adversarial network (BAGAN) for depth-image-based rendering (DIBR) 3D image watermarking to protect the image copyright. Convolutional block operations are employed to extract main image features for robust watermarking, but embedding watermark into some features will degrade image quality much. To relieve this kind of image distortion, the bilateral attention module (BAM) is utilized by mining correlations of the center view and the depth map to compute attention of the 3D image for guiding watermark to distribute over different image regions. Since a modality gap exists between the center view and the depth map, a cross-modal feature fusion module (CMFFM) is designed for BAM to bridge the cross-view gap. Because the depth map has lots of flat background information including many redundant features, to prune them, the depth redundancy elimination module (DREM) is used for cross-view feature fusion. In the decoder, two extractors with the same structure are built to recover watermark from the center view and the synthesized view, respectively. In addition, the discriminator is supposed to build a competitive relationship with the encoder to increase the image quality. The noise sub-network is used to train different image attacks for robustness. Extensive experimental results have demonstrated that the proposed BAGAN can obtain higher watermarking invisibility and robustness compared with existing DIBR 3D watermarking methods. Ablation experiments have also proven the effectiveness of DREM, CMFFM and BAM on BAGAN." @default.
- W4321792645 created "2023-02-25" @default.
- W4321792645 creator A5016817726 @default.
- W4321792645 creator A5018899373 @default.
- W4321792645 creator A5029507095 @default.
- W4321792645 creator A5030642173 @default.
- W4321792645 creator A5060792504 @default.
- W4321792645 date "2023-04-01" @default.
- W4321792645 modified "2023-10-15" @default.
- W4321792645 title "A bilateral attention based generative adversarial network for DIBR 3D image watermarking" @default.
- W4321792645 cites W1923184257 @default.
- W4321792645 cites W1968405684 @default.
- W4321792645 cites W2016416397 @default.
- W4321792645 cites W2079836831 @default.
- W4321792645 cites W2119781527 @default.
- W4321792645 cites W2120736986 @default.
- W4321792645 cites W2133255058 @default.
- W4321792645 cites W2161141427 @default.
- W4321792645 cites W2191747680 @default.
- W4321792645 cites W2231914250 @default.
- W4321792645 cites W2424641053 @default.
- W4321792645 cites W2467400645 @default.
- W4321792645 cites W2539358016 @default.
- W4321792645 cites W2614772934 @default.
- W4321792645 cites W2883233582 @default.
- W4321792645 cites W2964320807 @default.
- W4321792645 cites W2982163850 @default.
- W4321792645 cites W2997594966 @default.
- W4321792645 cites W3025169815 @default.
- W4321792645 cites W3035671550 @default.
- W4321792645 cites W3094229529 @default.
- W4321792645 cites W3097053213 @default.
- W4321792645 cites W3109263210 @default.
- W4321792645 cites W3116958493 @default.
- W4321792645 cites W3120113457 @default.
- W4321792645 cites W3129165028 @default.
- W4321792645 cites W3135872251 @default.
- W4321792645 cites W3136021864 @default.
- W4321792645 cites W3172255276 @default.
- W4321792645 cites W3174422331 @default.
- W4321792645 cites W3176231905 @default.
- W4321792645 cites W3185788529 @default.
- W4321792645 cites W3187751092 @default.
- W4321792645 cites W3211443677 @default.
- W4321792645 cites W3212180552 @default.
- W4321792645 cites W4200083849 @default.
- W4321792645 cites W4200292189 @default.
- W4321792645 cites W4206425634 @default.
- W4321792645 cites W4206646245 @default.
- W4321792645 cites W4214851787 @default.
- W4321792645 cites W4226017195 @default.
- W4321792645 cites W4229334014 @default.
- W4321792645 cites W4280554660 @default.
- W4321792645 cites W4286655178 @default.
- W4321792645 cites W4292615628 @default.
- W4321792645 cites W4319068851 @default.
- W4321792645 doi "https://doi.org/10.1016/j.jvcir.2023.103794" @default.
- W4321792645 hasPublicationYear "2023" @default.
- W4321792645 type Work @default.
- W4321792645 citedByCount "0" @default.
- W4321792645 crossrefType "journal-article" @default.
- W4321792645 hasAuthorship W4321792645A5016817726 @default.
- W4321792645 hasAuthorship W4321792645A5018899373 @default.
- W4321792645 hasAuthorship W4321792645A5029507095 @default.
- W4321792645 hasAuthorship W4321792645A5030642173 @default.
- W4321792645 hasAuthorship W4321792645A5060792504 @default.
- W4321792645 hasConcept C104317684 @default.
- W4321792645 hasConcept C115961682 @default.
- W4321792645 hasConcept C11727466 @default.
- W4321792645 hasConcept C138885662 @default.
- W4321792645 hasConcept C150817343 @default.
- W4321792645 hasConcept C154945302 @default.
- W4321792645 hasConcept C164112704 @default.
- W4321792645 hasConcept C185592680 @default.
- W4321792645 hasConcept C205711294 @default.
- W4321792645 hasConcept C2776401178 @default.
- W4321792645 hasConcept C2779803651 @default.
- W4321792645 hasConcept C2988773926 @default.
- W4321792645 hasConcept C31972630 @default.
- W4321792645 hasConcept C41008148 @default.
- W4321792645 hasConcept C41895202 @default.
- W4321792645 hasConcept C55020928 @default.
- W4321792645 hasConcept C55493867 @default.
- W4321792645 hasConcept C63479239 @default.
- W4321792645 hasConcept C76155785 @default.
- W4321792645 hasConcept C81363708 @default.
- W4321792645 hasConcept C94915269 @default.
- W4321792645 hasConceptScore W4321792645C104317684 @default.
- W4321792645 hasConceptScore W4321792645C115961682 @default.
- W4321792645 hasConceptScore W4321792645C11727466 @default.
- W4321792645 hasConceptScore W4321792645C138885662 @default.
- W4321792645 hasConceptScore W4321792645C150817343 @default.
- W4321792645 hasConceptScore W4321792645C154945302 @default.
- W4321792645 hasConceptScore W4321792645C164112704 @default.
- W4321792645 hasConceptScore W4321792645C185592680 @default.
- W4321792645 hasConceptScore W4321792645C205711294 @default.
- W4321792645 hasConceptScore W4321792645C2776401178 @default.
- W4321792645 hasConceptScore W4321792645C2779803651 @default.