FMSA: Frequency‐Matching and Spatial Attention for Image Style Transfer

ABSTRACT Arbitrary style transfer, a highly flexible technique with broad application potential, has gained significant attention recently. However, effectively disentangling content and style to synthesize novel stylized images remains a major challenge in arbitrary style transfer tasks. Existing methods primarily perform content and style disentanglement in either a single spatial domain or the frequency domain. We propose a style transfer method based on frequency‐matching and spatial attention called FMSA. FMSA consists of two components: frequency feature matching (FFM) and adaptive spatial attention (ASA). In the spatial domain, an attention mechanism is employed to learn attention scores from the content and style feature maps. These scores are then used to perform point‐wise normalization, generating synthesized features. In the frequency domain, filters are first applied to process the content and style features. The style‐transferred features are subsequently aligned with the magnitude of the style features and the phase of the content features, thereby achieving content‐style disentanglement and reconstruction. We introduce a frequency domain loss to reinforce content consistency in the stylized image while effectively transferring the style patterns to improve image synthesis quality. In addition, we design a decoder based on fast fourier convolution (FFC) that can efficiently decode both global and local information to produce the output. Extensive quantitative and qualitative experiments have demonstrated that the proposed method exhibits superior performance in style transfer tasks, generating results with enhanced stylistic patterns and visual quality. Project page: https://github.com/crFlower/FMSA