All-to-key Attention for Arbitrary Style Transfer
Attention-based arbitrary style transfer studies have shown promising performance in synthesizing vivid local style details. They typically use the all-to-all attention mechanism -- each position of content features is fully matched to all positions of style features. However, all-to-all attention tends to generate distorted style patterns and has quadratic complexity, limiting the effectiveness and efficiency of arbitrary style transfer. In this paper, we propose a novel all-to-key attention mechanism -- each position of content features is matched to stable key positions of style features -- that is more in line with the characteristics of style transfer. Specifically, it integrates two newly proposed attention forms: distributed and progressive attention. Distributed attention assigns attention to key style representations that depict the style distribution of local regions; Progressive attention pays attention from coarse-grained regions to fine-grained key positions. The resultant module, dubbed StyA2K, shows extraordinary performance in preserving the semantic structure and rendering consistent style patterns. Qualitative and quantitative comparisons with state-of-the-art methods demonstrate the superior performance of our approach.
Code (1)
Tasks
AllPositionStyle TransferSimilar Papers 제목 키워드 기반
AEANet: Affinity Enhanced Attentional Networks for Arbitrary Style Transfer
Arbitrary artistic style transfer is a research area that combines rational academic study with emotive artistic creation. It aims to create a new image from a content image according to a target artistic style, maintain…
Style TransferName Your Style: An Arbitrary Artist-aware Image Style Transfer
Image style transfer has attracted widespread attention in the past few years. Despite its remarkable results, it requires additional style images available as references, making it less flexible and inconvenient. Using …
Style TransferSCSA: A Plug-and-Play Semantic Continuous-Sparse Attention for Arbitrary Semantic Style Transfer
Attention-based arbitrary style transfer methods, including CNN-based, Transformer-based, and Diffusion-based, have flourished and produced high-quality stylized images. However, they perform poorly on the content an…
Style TransferArbitrary Style Transfer with Style-Attentional Networks
Arbitrary style transfer aims to synthesize a content image with the style of an image to create a third image that has never been seen before. Recent arbitrary style transfer algorithms find it challenging to balance th…
DecoderStyle TransferAdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
Fast arbitrary neural style transfer has attracted widespread attention from academic, industrial and art communities due to its flexibility in enabling various applications. Existing solutions either attentively fuse de…
Style TransferVideo Style Transfer