Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385201501> ?p ?o ?g. }
- W4385201501 endingPage "3686" @default.
- W4385201501 startingPage "3686" @default.
- W4385201501 abstract "In the depth map obtained through binocular stereo matching, there are many ill regions due to reasons such as lighting or occlusion. These ill regions cannot be accurately obtained due to the lack of information required for matching. Since the completion model based on Gan generates random results, it cannot accurately complete the depth map. Therefore, it is necessary to accurately complete the depth map according to reality. To address this issue, this paper proposes a depth information precise completion GAN (DIPC-GAN) that effectively uses the Guid layer normalization (GuidLN) module to guide the model for precise completion by utilizing depth edges. GuidLN flexibly adjusts the weights of the guiding conditions based on intermediate results, allowing modules to accurately and effectively incorporate the guiding information. The model employs multiscale discriminators to discriminate results of different resolutions at different generator stages, enhancing the generator’s grasp of overall image and detail information. Additionally, this paper proposes Attention-ResBlock, which enables all ResBlocks in each task module of the GAN-based multitask model to focus on their own task by sharing a mask. Even when the ill regions are large, the model can effectively complement the missing details in these regions. Additionally, the multiscale discriminator in the model enhances the generator’s robustness. Finally, the proposed task-specific residual module can effectively focus different subnetworks of a multitask model on their respective tasks. The model has shown good repair results on datasets, including artificial, real, and remote sensing images. The final experimental results showed that the model’s REL and RMSE decreased by 9.3% and 9.7%, respectively, compared to RDFGan." @default.
- W4385201501 created "2023-07-25" @default.
- W4385201501 creator A5018679381 @default.
- W4385201501 creator A5046380471 @default.
- W4385201501 creator A5053225991 @default.
- W4385201501 creator A5077216460 @default.
- W4385201501 creator A5078656823 @default.
- W4385201501 creator A5083707313 @default.
- W4385201501 creator A5086430006 @default.
- W4385201501 creator A5089180350 @default.
- W4385201501 date "2023-07-24" @default.
- W4385201501 modified "2023-09-30" @default.
- W4385201501 title "Depth Information Precise Completion-GAN: A Precisely Guided Method for Completing Ill Regions in Depth Maps" @default.
- W4385201501 cites W125693051 @default.
- W4385201501 cites W2073059412 @default.
- W4385201501 cites W2736830261 @default.
- W4385201501 cites W2794739174 @default.
- W4385201501 cites W2801093245 @default.
- W4385201501 cites W2885085354 @default.
- W4385201501 cites W2914484729 @default.
- W4385201501 cites W2920119658 @default.
- W4385201501 cites W2961926014 @default.
- W4385201501 cites W2963045776 @default.
- W4385201501 cites W2963316641 @default.
- W4385201501 cites W2963416674 @default.
- W4385201501 cites W2969202876 @default.
- W4385201501 cites W2982138396 @default.
- W4385201501 cites W2998293366 @default.
- W4385201501 cites W3009783082 @default.
- W4385201501 cites W3096831136 @default.
- W4385201501 cites W3109128945 @default.
- W4385201501 cites W3126423155 @default.
- W4385201501 cites W3127062510 @default.
- W4385201501 cites W3165495321 @default.
- W4385201501 cites W3174175265 @default.
- W4385201501 cites W3189360099 @default.
- W4385201501 cites W3206335707 @default.
- W4385201501 cites W4205402677 @default.
- W4385201501 cites W4206165093 @default.
- W4385201501 cites W4213207493 @default.
- W4385201501 cites W4307429261 @default.
- W4385201501 cites W4312793957 @default.
- W4385201501 cites W4312901872 @default.
- W4385201501 cites W4313151263 @default.
- W4385201501 doi "https://doi.org/10.3390/rs15143686" @default.
- W4385201501 hasPublicationYear "2023" @default.
- W4385201501 type Work @default.
- W4385201501 citedByCount "0" @default.
- W4385201501 crossrefType "journal-article" @default.
- W4385201501 hasAuthorship W4385201501A5018679381 @default.
- W4385201501 hasAuthorship W4385201501A5046380471 @default.
- W4385201501 hasAuthorship W4385201501A5053225991 @default.
- W4385201501 hasAuthorship W4385201501A5077216460 @default.
- W4385201501 hasAuthorship W4385201501A5078656823 @default.
- W4385201501 hasAuthorship W4385201501A5083707313 @default.
- W4385201501 hasAuthorship W4385201501A5086430006 @default.
- W4385201501 hasAuthorship W4385201501A5089180350 @default.
- W4385201501 hasBestOaLocation W43852015011 @default.
- W4385201501 hasConcept C104317684 @default.
- W4385201501 hasConcept C120665830 @default.
- W4385201501 hasConcept C121332964 @default.
- W4385201501 hasConcept C153180895 @default.
- W4385201501 hasConcept C154945302 @default.
- W4385201501 hasConcept C162324750 @default.
- W4385201501 hasConcept C163258240 @default.
- W4385201501 hasConcept C171268870 @default.
- W4385201501 hasConcept C185592680 @default.
- W4385201501 hasConcept C187736073 @default.
- W4385201501 hasConcept C192209626 @default.
- W4385201501 hasConcept C199360897 @default.
- W4385201501 hasConcept C2779803651 @default.
- W4385201501 hasConcept C2780451532 @default.
- W4385201501 hasConcept C2780992000 @default.
- W4385201501 hasConcept C31972630 @default.
- W4385201501 hasConcept C41008148 @default.
- W4385201501 hasConcept C55493867 @default.
- W4385201501 hasConcept C62520636 @default.
- W4385201501 hasConcept C63479239 @default.
- W4385201501 hasConcept C76155785 @default.
- W4385201501 hasConcept C94915269 @default.
- W4385201501 hasConceptScore W4385201501C104317684 @default.
- W4385201501 hasConceptScore W4385201501C120665830 @default.
- W4385201501 hasConceptScore W4385201501C121332964 @default.
- W4385201501 hasConceptScore W4385201501C153180895 @default.
- W4385201501 hasConceptScore W4385201501C154945302 @default.
- W4385201501 hasConceptScore W4385201501C162324750 @default.
- W4385201501 hasConceptScore W4385201501C163258240 @default.
- W4385201501 hasConceptScore W4385201501C171268870 @default.
- W4385201501 hasConceptScore W4385201501C185592680 @default.
- W4385201501 hasConceptScore W4385201501C187736073 @default.
- W4385201501 hasConceptScore W4385201501C192209626 @default.
- W4385201501 hasConceptScore W4385201501C199360897 @default.
- W4385201501 hasConceptScore W4385201501C2779803651 @default.
- W4385201501 hasConceptScore W4385201501C2780451532 @default.
- W4385201501 hasConceptScore W4385201501C2780992000 @default.
- W4385201501 hasConceptScore W4385201501C31972630 @default.
- W4385201501 hasConceptScore W4385201501C41008148 @default.
- W4385201501 hasConceptScore W4385201501C55493867 @default.