Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310426926> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4310426926 abstract "Arbitrary style transfer (AST) transfers arbitrary artistic styles onto content images. Despite the recent rapid progress, existing AST methods are either incapable or too slow to run at ultra-resolutions (e.g., 4K) with limited resources, which heavily hinders their further applications. In this paper, we tackle this dilemma by learning a straightforward and lightweight model, dubbed MicroAST. The key insight is to completely abandon the use of cumbersome pre-trained Deep Convolutional Neural Networks (e.g., VGG) at inference. Instead, we design two micro encoders (content and style encoders) and one micro decoder for style transfer. The content encoder aims at extracting the main structure of the content image. The style encoder, coupled with a modulator, encodes the style image into learnable dual-modulation signals that modulate both intermediate features and convolutional filters of the decoder, thus injecting more sophisticated and flexible style signals to guide the stylizations. In addition, to boost the ability of the style encoder to extract more distinct and representative style signals, we also introduce a new style signal contrastive loss in our model. Compared to the state of the art, our MicroAST not only produces visually superior results but also is 5-73 times smaller and 6-18 times faster, for the first time enabling super-fast (about 0.5 seconds) AST at 4K ultra-resolutions. Code is available at https://github.com/EndyWon/MicroAST." @default.
- W4310426926 created "2022-12-10" @default.
- W4310426926 creator A5017377137 @default.
- W4310426926 creator A5029851581 @default.
- W4310426926 creator A5042995511 @default.
- W4310426926 creator A5050960677 @default.
- W4310426926 creator A5052297489 @default.
- W4310426926 creator A5053735764 @default.
- W4310426926 creator A5055261896 @default.
- W4310426926 date "2022-11-28" @default.
- W4310426926 modified "2023-10-16" @default.
- W4310426926 title "MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer" @default.
- W4310426926 doi "https://doi.org/10.48550/arxiv.2211.15313" @default.
- W4310426926 hasPublicationYear "2022" @default.
- W4310426926 type Work @default.
- W4310426926 citedByCount "0" @default.
- W4310426926 crossrefType "posted-content" @default.
- W4310426926 hasAuthorship W4310426926A5017377137 @default.
- W4310426926 hasAuthorship W4310426926A5029851581 @default.
- W4310426926 hasAuthorship W4310426926A5042995511 @default.
- W4310426926 hasAuthorship W4310426926A5050960677 @default.
- W4310426926 hasAuthorship W4310426926A5052297489 @default.
- W4310426926 hasAuthorship W4310426926A5053735764 @default.
- W4310426926 hasAuthorship W4310426926A5055261896 @default.
- W4310426926 hasBestOaLocation W43104269261 @default.
- W4310426926 hasConcept C111919701 @default.
- W4310426926 hasConcept C118505674 @default.
- W4310426926 hasConcept C154945302 @default.
- W4310426926 hasConcept C166957645 @default.
- W4310426926 hasConcept C173608175 @default.
- W4310426926 hasConcept C177264268 @default.
- W4310426926 hasConcept C199360897 @default.
- W4310426926 hasConcept C2776175482 @default.
- W4310426926 hasConcept C2776214188 @default.
- W4310426926 hasConcept C2776445246 @default.
- W4310426926 hasConcept C2776760102 @default.
- W4310426926 hasConcept C2779843651 @default.
- W4310426926 hasConcept C41008148 @default.
- W4310426926 hasConcept C81363708 @default.
- W4310426926 hasConcept C95457728 @default.
- W4310426926 hasConceptScore W4310426926C111919701 @default.
- W4310426926 hasConceptScore W4310426926C118505674 @default.
- W4310426926 hasConceptScore W4310426926C154945302 @default.
- W4310426926 hasConceptScore W4310426926C166957645 @default.
- W4310426926 hasConceptScore W4310426926C173608175 @default.
- W4310426926 hasConceptScore W4310426926C177264268 @default.
- W4310426926 hasConceptScore W4310426926C199360897 @default.
- W4310426926 hasConceptScore W4310426926C2776175482 @default.
- W4310426926 hasConceptScore W4310426926C2776214188 @default.
- W4310426926 hasConceptScore W4310426926C2776445246 @default.
- W4310426926 hasConceptScore W4310426926C2776760102 @default.
- W4310426926 hasConceptScore W4310426926C2779843651 @default.
- W4310426926 hasConceptScore W4310426926C41008148 @default.
- W4310426926 hasConceptScore W4310426926C81363708 @default.
- W4310426926 hasConceptScore W4310426926C95457728 @default.
- W4310426926 hasLocation W43104269261 @default.
- W4310426926 hasLocation W43104269262 @default.
- W4310426926 hasOpenAccess W4310426926 @default.
- W4310426926 hasPrimaryLocation W43104269261 @default.
- W4310426926 hasRelatedWork W2275988210 @default.
- W4310426926 hasRelatedWork W2385621972 @default.
- W4310426926 hasRelatedWork W2521062615 @default.
- W4310426926 hasRelatedWork W2735477435 @default.
- W4310426926 hasRelatedWork W2807436399 @default.
- W4310426926 hasRelatedWork W3016958897 @default.
- W4310426926 hasRelatedWork W3045739591 @default.
- W4310426926 hasRelatedWork W3181746755 @default.
- W4310426926 hasRelatedWork W4283379348 @default.
- W4310426926 hasRelatedWork W4312417841 @default.
- W4310426926 isParatext "false" @default.
- W4310426926 isRetracted "false" @default.
- W4310426926 workType "article" @default.