FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295137553> ?p ?o ?g. }

• W4295137553 endingPage "103740" @default.
• W4295137553 startingPage "103740" @default.
• W4295137553 abstract "The quality of images captured in rainy days is severely degraded, which affects the accuracy of subsequent computer vision tasks. Recently, many deep learning-based methods have demonstrated superior performance for single image deraining. However, there are still many issues left. Since real-world rain images and their corresponding ground truths are difficult to collect, models trained on limited data may lead to overfitting. Meanwhile, although many methods can remove part of the rain streaks, most of them cannot reconstruct precise edges and textures. For the first issue, we use the transfer learning approach. Loading pre-trained parameters trained on the ImageNet enables the network to have robust feature representation, which improves the generalization of the network. For the second issue, we restore clear details by making full use of the frequency domain information of the image. Specifically, we design a novel frequency domain residual block (FRDB) and use an efficient fusion strategy in FRDB to fuse spatial and frequency domain features. Then, we propose a frequency domain reconstruction loss function (FDR loss) to restore details by reducing the differences in high-frequency space. Finally, a simple detail enhancement attention module (DEAM) is used to further enhance the image details. Extensive experimental results demonstrate that our DPNet has superior performance on both synthetic and real data. Furthermore, we verify the effectiveness of our method on downstream computer vision tasks. The source codes will be open at https://github.com/noxsine/DPNet ." @default.
• W4295137553 created "2022-09-11" @default.
• W4295137553 creator A5038174569 @default.
• W4295137553 creator A5067650828 @default.
• W4295137553 creator A5069672411 @default.
• W4295137553 creator A5078311909 @default.
• W4295137553 date "2022-10-01" @default.
• W4295137553 modified "2023-10-17" @default.
• W4295137553 title "DPNet: Detail-preserving image deraining via learning frequency domain knowledge" @default.
• W4295137553 cites W2046119925 @default.
• W4295137553 cites W2114770744 @default.
• W4295137553 cites W2133665775 @default.
• W4295137553 cites W2141983208 @default.
• W4295137553 cites W2165698076 @default.
• W4295137553 cites W2509784253 @default.
• W4295137553 cites W2928165649 @default.
• W4295137553 cites W2963017889 @default.
• W4295137553 cites W2964267765 @default.
• W4295137553 cites W2985321619 @default.
• W4295137553 cites W3021494530 @default.
• W4295137553 cites W3095523882 @default.
• W4295137553 cites W3135260009 @default.
• W4295137553 cites W3139232844 @default.
• W4295137553 cites W3164401850 @default.
• W4295137553 cites W3193296307 @default.
• W4295137553 cites W3194255522 @default.
• W4295137553 cites W3214101316 @default.
• W4295137553 cites W3216483416 @default.
• W4295137553 cites W4205268584 @default.
• W4295137553 doi "https://doi.org/10.1016/j.dsp.2022.103740" @default.
• W4295137553 hasPublicationYear "2022" @default.
• W4295137553 type Work @default.
• W4295137553 citedByCount "3" @default.
• W4295137553 countsByYear W42951375532022 @default.
• W4295137553 countsByYear W42951375532023 @default.
• W4295137553 crossrefType "journal-article" @default.
• W4295137553 hasAuthorship W4295137553A5038174569 @default.
• W4295137553 hasAuthorship W4295137553A5067650828 @default.
• W4295137553 hasAuthorship W4295137553A5069672411 @default.
• W4295137553 hasAuthorship W4295137553A5078311909 @default.
• W4295137553 hasConcept C115961682 @default.
• W4295137553 hasConcept C119599485 @default.
• W4295137553 hasConcept C119857082 @default.
• W4295137553 hasConcept C127413603 @default.
• W4295137553 hasConcept C134306372 @default.
• W4295137553 hasConcept C138885662 @default.
• W4295137553 hasConcept C141353440 @default.
• W4295137553 hasConcept C150899416 @default.
• W4295137553 hasConcept C153180895 @default.
• W4295137553 hasConcept C154945302 @default.
• W4295137553 hasConcept C177148314 @default.
• W4295137553 hasConcept C19118579 @default.
• W4295137553 hasConcept C22019652 @default.
• W4295137553 hasConcept C2524010 @default.
• W4295137553 hasConcept C2776401178 @default.
• W4295137553 hasConcept C2777210771 @default.
• W4295137553 hasConcept C31972630 @default.
• W4295137553 hasConcept C33923547 @default.
• W4295137553 hasConcept C41008148 @default.
• W4295137553 hasConcept C41895202 @default.
• W4295137553 hasConcept C50644808 @default.
• W4295137553 hasConceptScore W4295137553C115961682 @default.
• W4295137553 hasConceptScore W4295137553C119599485 @default.
• W4295137553 hasConceptScore W4295137553C119857082 @default.
• W4295137553 hasConceptScore W4295137553C127413603 @default.
• W4295137553 hasConceptScore W4295137553C134306372 @default.
• W4295137553 hasConceptScore W4295137553C138885662 @default.
• W4295137553 hasConceptScore W4295137553C141353440 @default.
• W4295137553 hasConceptScore W4295137553C150899416 @default.
• W4295137553 hasConceptScore W4295137553C153180895 @default.
• W4295137553 hasConceptScore W4295137553C154945302 @default.
• W4295137553 hasConceptScore W4295137553C177148314 @default.
• W4295137553 hasConceptScore W4295137553C19118579 @default.
• W4295137553 hasConceptScore W4295137553C22019652 @default.
• W4295137553 hasConceptScore W4295137553C2524010 @default.
• W4295137553 hasConceptScore W4295137553C2776401178 @default.
• W4295137553 hasConceptScore W4295137553C2777210771 @default.
• W4295137553 hasConceptScore W4295137553C31972630 @default.
• W4295137553 hasConceptScore W4295137553C33923547 @default.
• W4295137553 hasConceptScore W4295137553C41008148 @default.
• W4295137553 hasConceptScore W4295137553C41895202 @default.
• W4295137553 hasConceptScore W4295137553C50644808 @default.
• W4295137553 hasFunder F4320321001 @default.
• W4295137553 hasLocation W42951375531 @default.
• W4295137553 hasOpenAccess W4295137553 @default.
• W4295137553 hasPrimaryLocation W42951375531 @default.
• W4295137553 hasRelatedWork W2912737833 @default.
• W4295137553 hasRelatedWork W2942629287 @default.
• W4295137553 hasRelatedWork W2989932438 @default.
• W4295137553 hasRelatedWork W3099765033 @default.
• W4295137553 hasRelatedWork W3175189414 @default.
• W4295137553 hasRelatedWork W3186919929 @default.
• W4295137553 hasRelatedWork W4210794429 @default.
• W4295137553 hasRelatedWork W4304128395 @default.
• W4295137553 hasRelatedWork W4313289428 @default.
• W4295137553 hasRelatedWork W4320737025 @default.
• W4295137553 hasVolume "130" @default.
• W4295137553 isParatext "false" @default.

• next