Region-controlled Style Transfer
This work addresses a specific limitation in image style transfer for computational vision applications, representing an incremental improvement.
The paper tackles the problem of controlling style transfer strength in different image regions by proposing a training method with a region-specific loss function and a novel feature fusion technique, achieving effective results as demonstrated in experiments.
Image style transfer is a challenging task in computational vision. Existing algorithms transfer the color and texture of style images by controlling the neural network's feature layers. However, they fail to control the strength of textures in different regions of the content image. To address this issue, we propose a training method that uses a loss function to constrain the style intensity in different regions. This method guides the transfer strength of style features in different regions based on the gradient relationship between style and content images. Additionally, we introduce a novel feature fusion method that linearly transforms content features to resemble style features while preserving their semantic relationships. Extensive experiments have demonstrated the effectiveness of our proposed approach.