Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386075655> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4386075655 abstract "Vector font synthesis is a challenging and ongoing problem in the fields of Computer Vision and Computer Graphics. The recently-proposed DeepVecFont [27] achieved state-of-the-art performance by exploiting information of both the image and sequence modalities of vector fonts. However, it has limited capability for handling long sequence data and heavily relies on an image-guided outline refinement post-processing. Thus, vector glyphs synthesized by DeepVecFont still often contain some distortions and artifacts and cannot rival human-designed results. To address the above problems, this paper proposes an enhanced version of DeepVecFont mainly by making the following three novel technical contributions. First, we adopt Transformers instead of RNNs to process sequential data and design a relaxation representation for vector outlines, markedly improving the model's capability and stability of synthesizing long and complex outlines. Second, we propose to sample auxiliary points in addition to control points to precisely align the generated and target Bézier curves or lines. Finally, to alleviate error accumulation in the sequential generation process, we develop a context-based self-refinement module based on another Transformer-based decoder to remove artifacts in the initially synthesized glyphs. Both qualitative and quantitative results demonstrate that the proposed method effectively resolves those intrinsic problems of the original DeepVecFont and outperforms existing approaches in generating English and Chinese vector fonts with complicated structures and diverse styles." @default.
- W4386075655 created "2023-08-23" @default.
- W4386075655 creator A5002863452 @default.
- W4386075655 creator A5049419584 @default.
- W4386075655 creator A5063600625 @default.
- W4386075655 creator A5083351215 @default.
- W4386075655 creator A5090655358 @default.
- W4386075655 date "2023-06-01" @default.
- W4386075655 modified "2023-10-18" @default.
- W4386075655 title "DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality" @default.
- W4386075655 cites W2064675550 @default.
- W4386075655 cites W2069728322 @default.
- W4386075655 cites W2603777577 @default.
- W4386075655 cites W2905330967 @default.
- W4386075655 cites W2962968458 @default.
- W4386075655 cites W2963073614 @default.
- W4386075655 cites W2963801463 @default.
- W4386075655 cites W2963802693 @default.
- W4386075655 cites W2966583823 @default.
- W4386075655 cites W3048812656 @default.
- W4386075655 cites W3089089712 @default.
- W4386075655 cites W3098808043 @default.
- W4386075655 cites W3107232127 @default.
- W4386075655 cites W3167115472 @default.
- W4386075655 cites W4200524251 @default.
- W4386075655 cites W4235982336 @default.
- W4386075655 cites W4283329258 @default.
- W4386075655 cites W4312866973 @default.
- W4386075655 cites W4313181980 @default.
- W4386075655 doi "https://doi.org/10.1109/cvpr52729.2023.01757" @default.
- W4386075655 hasPublicationYear "2023" @default.
- W4386075655 type Work @default.
- W4386075655 citedByCount "0" @default.
- W4386075655 crossrefType "proceedings-article" @default.
- W4386075655 hasAuthorship W4386075655A5002863452 @default.
- W4386075655 hasAuthorship W4386075655A5049419584 @default.
- W4386075655 hasAuthorship W4386075655A5063600625 @default.
- W4386075655 hasAuthorship W4386075655A5083351215 @default.
- W4386075655 hasAuthorship W4386075655A5090655358 @default.
- W4386075655 hasConcept C111919701 @default.
- W4386075655 hasConcept C121332964 @default.
- W4386075655 hasConcept C121684516 @default.
- W4386075655 hasConcept C153180895 @default.
- W4386075655 hasConcept C154945302 @default.
- W4386075655 hasConcept C165801399 @default.
- W4386075655 hasConcept C202629362 @default.
- W4386075655 hasConcept C21442007 @default.
- W4386075655 hasConcept C31972630 @default.
- W4386075655 hasConcept C41008148 @default.
- W4386075655 hasConcept C59662460 @default.
- W4386075655 hasConcept C62520636 @default.
- W4386075655 hasConcept C66322947 @default.
- W4386075655 hasConcept C77660652 @default.
- W4386075655 hasConceptScore W4386075655C111919701 @default.
- W4386075655 hasConceptScore W4386075655C121332964 @default.
- W4386075655 hasConceptScore W4386075655C121684516 @default.
- W4386075655 hasConceptScore W4386075655C153180895 @default.
- W4386075655 hasConceptScore W4386075655C154945302 @default.
- W4386075655 hasConceptScore W4386075655C165801399 @default.
- W4386075655 hasConceptScore W4386075655C202629362 @default.
- W4386075655 hasConceptScore W4386075655C21442007 @default.
- W4386075655 hasConceptScore W4386075655C31972630 @default.
- W4386075655 hasConceptScore W4386075655C41008148 @default.
- W4386075655 hasConceptScore W4386075655C59662460 @default.
- W4386075655 hasConceptScore W4386075655C62520636 @default.
- W4386075655 hasConceptScore W4386075655C66322947 @default.
- W4386075655 hasConceptScore W4386075655C77660652 @default.
- W4386075655 hasLocation W43860756551 @default.
- W4386075655 hasOpenAccess W4386075655 @default.
- W4386075655 hasPrimaryLocation W43860756551 @default.
- W4386075655 hasRelatedWork W1486505043 @default.
- W4386075655 hasRelatedWork W2087166697 @default.
- W4386075655 hasRelatedWork W2148310037 @default.
- W4386075655 hasRelatedWork W2354624479 @default.
- W4386075655 hasRelatedWork W2368856929 @default.
- W4386075655 hasRelatedWork W2368984385 @default.
- W4386075655 hasRelatedWork W2392208963 @default.
- W4386075655 hasRelatedWork W2392464869 @default.
- W4386075655 hasRelatedWork W2394137533 @default.
- W4386075655 hasRelatedWork W2886945966 @default.
- W4386075655 isParatext "false" @default.
- W4386075655 isRetracted "false" @default.
- W4386075655 workType "article" @default.