Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288055295> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4288055295 abstract "State-of-the-art parametric and non-parametric style transfer approaches are prone to either distorted local style patterns due to global statistics alignment, or unpleasing artifacts resulting from patch mismatching. In this paper, we study a novel semi-parametric neural style transfer framework that alleviates the deficiency of both parametric and non-parametric stylization. The core idea of our approach is to establish accurate and fine-grained content-style correspondences using graph neural networks (GNNs). To this end, we develop an elaborated GNN model with content and style local patches as the graph vertices. The style transfer procedure is then modeled as the attention-based heterogeneous message passing between the style and content nodes in a learnable manner, leading to adaptive many-to-one style-content correlations at the local patch level. In addition, an elaborated deformable graph convolutional operation is introduced for cross-scale style-content matching. Experimental results demonstrate that the proposed semi-parametric image stylization approach yields encouraging results on the challenging style patterns, preserving both global appearance and exquisite details. Furthermore, by controlling the number of edges at the inference stage, the proposed method also triggers novel functionalities like diversified patch-based stylization with a single model." @default.
- W4288055295 created "2022-07-28" @default.
- W4288055295 creator A5009740359 @default.
- W4288055295 creator A5015574447 @default.
- W4288055295 creator A5018965769 @default.
- W4288055295 creator A5026532752 @default.
- W4288055295 creator A5074103823 @default.
- W4288055295 creator A5074468971 @default.
- W4288055295 creator A5074672983 @default.
- W4288055295 date "2022-07-24" @default.
- W4288055295 modified "2023-10-18" @default.
- W4288055295 title "Learning Graph Neural Networks for Image Style Transfer" @default.
- W4288055295 doi "https://doi.org/10.48550/arxiv.2207.11681" @default.
- W4288055295 hasPublicationYear "2022" @default.
- W4288055295 type Work @default.
- W4288055295 citedByCount "0" @default.
- W4288055295 crossrefType "posted-content" @default.
- W4288055295 hasAuthorship W4288055295A5009740359 @default.
- W4288055295 hasAuthorship W4288055295A5015574447 @default.
- W4288055295 hasAuthorship W4288055295A5018965769 @default.
- W4288055295 hasAuthorship W4288055295A5026532752 @default.
- W4288055295 hasAuthorship W4288055295A5074103823 @default.
- W4288055295 hasAuthorship W4288055295A5074468971 @default.
- W4288055295 hasAuthorship W4288055295A5074672983 @default.
- W4288055295 hasBestOaLocation W42880552951 @default.
- W4288055295 hasConcept C105795698 @default.
- W4288055295 hasConcept C117251300 @default.
- W4288055295 hasConcept C132525143 @default.
- W4288055295 hasConcept C153180895 @default.
- W4288055295 hasConcept C154945302 @default.
- W4288055295 hasConcept C165064840 @default.
- W4288055295 hasConcept C166957645 @default.
- W4288055295 hasConcept C2776214188 @default.
- W4288055295 hasConcept C2776445246 @default.
- W4288055295 hasConcept C33923547 @default.
- W4288055295 hasConcept C41008148 @default.
- W4288055295 hasConcept C50644808 @default.
- W4288055295 hasConcept C80444323 @default.
- W4288055295 hasConcept C81363708 @default.
- W4288055295 hasConcept C95457728 @default.
- W4288055295 hasConceptScore W4288055295C105795698 @default.
- W4288055295 hasConceptScore W4288055295C117251300 @default.
- W4288055295 hasConceptScore W4288055295C132525143 @default.
- W4288055295 hasConceptScore W4288055295C153180895 @default.
- W4288055295 hasConceptScore W4288055295C154945302 @default.
- W4288055295 hasConceptScore W4288055295C165064840 @default.
- W4288055295 hasConceptScore W4288055295C166957645 @default.
- W4288055295 hasConceptScore W4288055295C2776214188 @default.
- W4288055295 hasConceptScore W4288055295C2776445246 @default.
- W4288055295 hasConceptScore W4288055295C33923547 @default.
- W4288055295 hasConceptScore W4288055295C41008148 @default.
- W4288055295 hasConceptScore W4288055295C50644808 @default.
- W4288055295 hasConceptScore W4288055295C80444323 @default.
- W4288055295 hasConceptScore W4288055295C81363708 @default.
- W4288055295 hasConceptScore W4288055295C95457728 @default.
- W4288055295 hasLocation W42880552951 @default.
- W4288055295 hasOpenAccess W4288055295 @default.
- W4288055295 hasPrimaryLocation W42880552951 @default.
- W4288055295 hasRelatedWork W11942493 @default.
- W4288055295 hasRelatedWork W12336802 @default.
- W4288055295 hasRelatedWork W12551846 @default.
- W4288055295 hasRelatedWork W12892025 @default.
- W4288055295 hasRelatedWork W14719770 @default.
- W4288055295 hasRelatedWork W4136762 @default.
- W4288055295 hasRelatedWork W7122632 @default.
- W4288055295 hasRelatedWork W7408119 @default.
- W4288055295 hasRelatedWork W9190101 @default.
- W4288055295 hasRelatedWork W933276 @default.
- W4288055295 isParatext "false" @default.
- W4288055295 isRetracted "false" @default.
- W4288055295 workType "article" @default.