Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384919982> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4384919982 abstract "Manga is a fashionable Japanese-style comic form that is composed of black-and-white strokes and is generally displayed as raster images on digital devices. Typical mangas have simple textures, wide lines, and few color gradients, which are vectorizable natures to enjoy the merits of vector graphics, e.g., adaptive resolutions and small file sizes. In this paper, we propose MARVEL (MAnga's Raster to VEctor Learning), a primitive-wise approach for vectorizing raster mangas by Deep Reinforcement Learning (DRL). Unlike previous learning-based methods which predict vector parameters for an entire image, MARVEL introduces a new perspective that regards an entire manga as a collection of basic primitivestextemdash stroke lines, and designs a DRL model to decompose the target image into a primitive sequence for achieving accurate vectorization. To improve vectorization accuracies and decrease file sizes, we further propose a stroke accuracy reward to predict accurate stroke lines, and a pruning mechanism to avoid generating erroneous and repeated strokes. Extensive subjective and objective experiments show that our MARVEL can generate impressive results and reaches the state-of-the-art level. Our code is open-source at: https://github.com/SwordHolderSH/Mang2Vec." @default.
- W4384919982 created "2023-07-21" @default.
- W4384919982 creator A5013879989 @default.
- W4384919982 creator A5023444000 @default.
- W4384919982 creator A5051862250 @default.
- W4384919982 creator A5053316728 @default.
- W4384919982 creator A5065727485 @default.
- W4384919982 date "2021-10-10" @default.
- W4384919982 modified "2023-09-25" @default.
- W4384919982 title "MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning" @default.
- W4384919982 doi "https://doi.org/10.48550/arxiv.2110.04830" @default.
- W4384919982 hasPublicationYear "2021" @default.
- W4384919982 type Work @default.
- W4384919982 citedByCount "0" @default.
- W4384919982 crossrefType "posted-content" @default.
- W4384919982 hasAuthorship W4384919982A5013879989 @default.
- W4384919982 hasAuthorship W4384919982A5023444000 @default.
- W4384919982 hasAuthorship W4384919982A5051862250 @default.
- W4384919982 hasAuthorship W4384919982A5053316728 @default.
- W4384919982 hasAuthorship W4384919982A5065727485 @default.
- W4384919982 hasBestOaLocation W43849199821 @default.
- W4384919982 hasConcept C108010975 @default.
- W4384919982 hasConcept C121684516 @default.
- W4384919982 hasConcept C153180895 @default.
- W4384919982 hasConcept C154945302 @default.
- W4384919982 hasConcept C160633673 @default.
- W4384919982 hasConcept C173608175 @default.
- W4384919982 hasConcept C177264268 @default.
- W4384919982 hasConcept C181844469 @default.
- W4384919982 hasConcept C199360897 @default.
- W4384919982 hasConcept C21442007 @default.
- W4384919982 hasConcept C2776760102 @default.
- W4384919982 hasConcept C31972630 @default.
- W4384919982 hasConcept C41008148 @default.
- W4384919982 hasConcept C41681595 @default.
- W4384919982 hasConcept C59662460 @default.
- W4384919982 hasConcept C6557445 @default.
- W4384919982 hasConcept C86803240 @default.
- W4384919982 hasConcept C97541855 @default.
- W4384919982 hasConceptScore W4384919982C108010975 @default.
- W4384919982 hasConceptScore W4384919982C121684516 @default.
- W4384919982 hasConceptScore W4384919982C153180895 @default.
- W4384919982 hasConceptScore W4384919982C154945302 @default.
- W4384919982 hasConceptScore W4384919982C160633673 @default.
- W4384919982 hasConceptScore W4384919982C173608175 @default.
- W4384919982 hasConceptScore W4384919982C177264268 @default.
- W4384919982 hasConceptScore W4384919982C181844469 @default.
- W4384919982 hasConceptScore W4384919982C199360897 @default.
- W4384919982 hasConceptScore W4384919982C21442007 @default.
- W4384919982 hasConceptScore W4384919982C2776760102 @default.
- W4384919982 hasConceptScore W4384919982C31972630 @default.
- W4384919982 hasConceptScore W4384919982C41008148 @default.
- W4384919982 hasConceptScore W4384919982C41681595 @default.
- W4384919982 hasConceptScore W4384919982C59662460 @default.
- W4384919982 hasConceptScore W4384919982C6557445 @default.
- W4384919982 hasConceptScore W4384919982C86803240 @default.
- W4384919982 hasConceptScore W4384919982C97541855 @default.
- W4384919982 hasLocation W43849199821 @default.
- W4384919982 hasOpenAccess W4384919982 @default.
- W4384919982 hasPrimaryLocation W43849199821 @default.
- W4384919982 hasRelatedWork W1970821708 @default.
- W4384919982 hasRelatedWork W2068367186 @default.
- W4384919982 hasRelatedWork W2533397633 @default.
- W4384919982 hasRelatedWork W3046395349 @default.
- W4384919982 hasRelatedWork W3170862559 @default.
- W4384919982 hasRelatedWork W4210244968 @default.
- W4384919982 hasRelatedWork W4301073684 @default.
- W4384919982 hasRelatedWork W4365563 @default.
- W4384919982 hasRelatedWork W604260942 @default.
- W4384919982 hasRelatedWork W2944365402 @default.
- W4384919982 isParatext "false" @default.
- W4384919982 isRetracted "false" @default.
- W4384919982 workType "article" @default.