Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387559996> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4387559996 abstract "Vector-quantized image modeling has shown great potential in synthesizing high-quality images. However, generating high-resolution images remains a challenging task due to the quadratic computational overhead of the self-attention process. In this study, we seek to explore a more efficient two-stage framework for high-resolution image generation with improvements in the following three aspects. (1) Based on the observation that the first quantization stage has solid local property, we employ a local attention-based quantization model instead of the global attention mechanism used in previous methods, leading to better efficiency and reconstruction quality. (2) We emphasize the importance of multi-grained feature interaction during image generation and introduce an efficient attention mechanism that combines global attention (long-range semantic consistency within the whole image) and local attention (fined-grained details). This approach results in faster generation speed, higher generation fidelity, and improved resolution. (3) We propose a new generation pipeline incorporating autoencoding training and autoregressive generation strategy, demonstrating a better paradigm for image synthesis. Extensive experiments demonstrate the superiority of our approach in high-quality and high-resolution image reconstruction and generation." @default.
- W4387559996 created "2023-10-12" @default.
- W4387559996 creator A5003662421 @default.
- W4387559996 creator A5019994258 @default.
- W4387559996 creator A5028693655 @default.
- W4387559996 creator A5052044793 @default.
- W4387559996 creator A5074916544 @default.
- W4387559996 creator A5078137455 @default.
- W4387559996 creator A5088762304 @default.
- W4387559996 date "2023-10-09" @default.
- W4387559996 modified "2023-10-18" @default.
- W4387559996 title "Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers" @default.
- W4387559996 doi "https://doi.org/10.48550/arxiv.2310.05400" @default.
- W4387559996 hasPublicationYear "2023" @default.
- W4387559996 type Work @default.
- W4387559996 citedByCount "0" @default.
- W4387559996 crossrefType "posted-content" @default.
- W4387559996 hasAuthorship W4387559996A5003662421 @default.
- W4387559996 hasAuthorship W4387559996A5019994258 @default.
- W4387559996 hasAuthorship W4387559996A5028693655 @default.
- W4387559996 hasAuthorship W4387559996A5052044793 @default.
- W4387559996 hasAuthorship W4387559996A5074916544 @default.
- W4387559996 hasAuthorship W4387559996A5078137455 @default.
- W4387559996 hasAuthorship W4387559996A5088762304 @default.
- W4387559996 hasBestOaLocation W43875599961 @default.
- W4387559996 hasConcept C115961682 @default.
- W4387559996 hasConcept C149782125 @default.
- W4387559996 hasConcept C154945302 @default.
- W4387559996 hasConcept C159877910 @default.
- W4387559996 hasConcept C199833920 @default.
- W4387559996 hasConcept C28855332 @default.
- W4387559996 hasConcept C31972630 @default.
- W4387559996 hasConcept C33923547 @default.
- W4387559996 hasConcept C41008148 @default.
- W4387559996 hasConcept C55020928 @default.
- W4387559996 hasConceptScore W4387559996C115961682 @default.
- W4387559996 hasConceptScore W4387559996C149782125 @default.
- W4387559996 hasConceptScore W4387559996C154945302 @default.
- W4387559996 hasConceptScore W4387559996C159877910 @default.
- W4387559996 hasConceptScore W4387559996C199833920 @default.
- W4387559996 hasConceptScore W4387559996C28855332 @default.
- W4387559996 hasConceptScore W4387559996C31972630 @default.
- W4387559996 hasConceptScore W4387559996C33923547 @default.
- W4387559996 hasConceptScore W4387559996C41008148 @default.
- W4387559996 hasConceptScore W4387559996C55020928 @default.
- W4387559996 hasLocation W43875599961 @default.
- W4387559996 hasOpenAccess W4387559996 @default.
- W4387559996 hasPrimaryLocation W43875599961 @default.
- W4387559996 hasRelatedWork W1520183331 @default.
- W4387559996 hasRelatedWork W1972271943 @default.
- W4387559996 hasRelatedWork W2099889858 @default.
- W4387559996 hasRelatedWork W2150410159 @default.
- W4387559996 hasRelatedWork W2168175994 @default.
- W4387559996 hasRelatedWork W3209251257 @default.
- W4387559996 hasRelatedWork W4287185323 @default.
- W4387559996 hasRelatedWork W4327525404 @default.
- W4387559996 hasRelatedWork W2171218219 @default.
- W4387559996 hasRelatedWork W3150905897 @default.
- W4387559996 isParatext "false" @default.
- W4387559996 isRetracted "false" @default.
- W4387559996 workType "article" @default.