Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312932020> ?p ?o ?g. }
- W4312932020 endingPage "379" @default.
- W4312932020 startingPage "363" @default.
- W4312932020 abstract "This study proposes a deep-learning framework for mesh denoising from a single noisy input, where two graph convolutional networks are trained jointly to filter vertex positions and facet normals apart. The prior obtained only from a single input is particularly referred to as a self-prior. The proposed method leverages the framework of the deep image prior (DIP), which obtains the self-prior for image restoration using a convolutional neural network (CNN). Thus, we obtain a denoised mesh without any ground-truth noise-free meshes. Compared to the original DIP that transforms a fixed random code into a noise-free image by the neural network, we reproduce vertex displacement from a fixed random code and reproduce facet normals from feature vectors that summarize local triangle arrangements. After tuning several hyperparameters with a few validation samples, our method achieved significantly higher performance than traditional approaches working with a single noisy input mesh. Moreover, its performance is better than the other methods using deep neural networks trained with a large-scale shape dataset. The independence of our method of either large-scale datasets or ground-truth noise-free mesh will allow us to easily denoise meshes whose shapes are rarely included in the shape datasets. Our code is available at: https://github.com/astaka-pe/Dual-DMP.git ." @default.
- W4312932020 created "2023-01-05" @default.
- W4312932020 creator A5049557830 @default.
- W4312932020 creator A5050584905 @default.
- W4312932020 creator A5058216244 @default.
- W4312932020 creator A5071419414 @default.
- W4312932020 date "2022-01-01" @default.
- W4312932020 modified "2023-10-01" @default.
- W4312932020 title "Learning Self-prior for Mesh Denoising Using Dual Graph Convolutional Networks" @default.
- W4312932020 cites W1974956622 @default.
- W4312932020 cites W1987648924 @default.
- W4312932020 cites W1990816220 @default.
- W4312932020 cites W2000214666 @default.
- W4312932020 cites W2016533289 @default.
- W4312932020 cites W2042460596 @default.
- W4312932020 cites W2092785747 @default.
- W4312932020 cites W2097869901 @default.
- W4312932020 cites W2105960593 @default.
- W4312932020 cites W2114275307 @default.
- W4312932020 cites W2116014169 @default.
- W4312932020 cites W2125065112 @default.
- W4312932020 cites W2287328596 @default.
- W4312932020 cites W2358992035 @default.
- W4312932020 cites W2551040565 @default.
- W4312932020 cites W2782659212 @default.
- W4312932020 cites W2793110797 @default.
- W4312932020 cites W2799349463 @default.
- W4312932020 cites W2891396148 @default.
- W4312932020 cites W2898167198 @default.
- W4312932020 cites W2902857081 @default.
- W4312932020 cites W2945485418 @default.
- W4312932020 cites W2964013315 @default.
- W4312932020 cites W2969633497 @default.
- W4312932020 cites W2973014570 @default.
- W4312932020 cites W2976401455 @default.
- W4312932020 cites W2998590421 @default.
- W4312932020 cites W3021053382 @default.
- W4312932020 cites W3035145671 @default.
- W4312932020 cites W3098337560 @default.
- W4312932020 cites W3101027576 @default.
- W4312932020 cites W3148091194 @default.
- W4312932020 cites W3173485944 @default.
- W4312932020 cites W3184811029 @default.
- W4312932020 cites W3191900174 @default.
- W4312932020 cites W3212309639 @default.
- W4312932020 cites W4214535475 @default.
- W4312932020 cites W4242723867 @default.
- W4312932020 doi "https://doi.org/10.1007/978-3-031-20062-5_21" @default.
- W4312932020 hasPublicationYear "2022" @default.
- W4312932020 type Work @default.
- W4312932020 citedByCount "0" @default.
- W4312932020 crossrefType "book-chapter" @default.
- W4312932020 hasAuthorship W4312932020A5049557830 @default.
- W4312932020 hasAuthorship W4312932020A5050584905 @default.
- W4312932020 hasAuthorship W4312932020A5058216244 @default.
- W4312932020 hasAuthorship W4312932020A5071419414 @default.
- W4312932020 hasConcept C108583219 @default.
- W4312932020 hasConcept C11413529 @default.
- W4312932020 hasConcept C115961682 @default.
- W4312932020 hasConcept C121684516 @default.
- W4312932020 hasConcept C132525143 @default.
- W4312932020 hasConcept C146849305 @default.
- W4312932020 hasConcept C153180895 @default.
- W4312932020 hasConcept C154945302 @default.
- W4312932020 hasConcept C163294075 @default.
- W4312932020 hasConcept C177264268 @default.
- W4312932020 hasConcept C199360897 @default.
- W4312932020 hasConcept C2776760102 @default.
- W4312932020 hasConcept C31487907 @default.
- W4312932020 hasConcept C41008148 @default.
- W4312932020 hasConcept C80444323 @default.
- W4312932020 hasConcept C80899671 @default.
- W4312932020 hasConcept C81363708 @default.
- W4312932020 hasConcept C8642999 @default.
- W4312932020 hasConcept C99498987 @default.
- W4312932020 hasConceptScore W4312932020C108583219 @default.
- W4312932020 hasConceptScore W4312932020C11413529 @default.
- W4312932020 hasConceptScore W4312932020C115961682 @default.
- W4312932020 hasConceptScore W4312932020C121684516 @default.
- W4312932020 hasConceptScore W4312932020C132525143 @default.
- W4312932020 hasConceptScore W4312932020C146849305 @default.
- W4312932020 hasConceptScore W4312932020C153180895 @default.
- W4312932020 hasConceptScore W4312932020C154945302 @default.
- W4312932020 hasConceptScore W4312932020C163294075 @default.
- W4312932020 hasConceptScore W4312932020C177264268 @default.
- W4312932020 hasConceptScore W4312932020C199360897 @default.
- W4312932020 hasConceptScore W4312932020C2776760102 @default.
- W4312932020 hasConceptScore W4312932020C31487907 @default.
- W4312932020 hasConceptScore W4312932020C41008148 @default.
- W4312932020 hasConceptScore W4312932020C80444323 @default.
- W4312932020 hasConceptScore W4312932020C80899671 @default.
- W4312932020 hasConceptScore W4312932020C81363708 @default.
- W4312932020 hasConceptScore W4312932020C8642999 @default.
- W4312932020 hasConceptScore W4312932020C99498987 @default.
- W4312932020 hasLocation W43129320201 @default.
- W4312932020 hasOpenAccess W4312932020 @default.
- W4312932020 hasPrimaryLocation W43129320201 @default.
- W4312932020 hasRelatedWork W2732542196 @default.