Multi-scaled attentive style transfer based on dilated convolution
Xuefeng Xu, Tuo Chen, Huanyi Chen · Applied and Computational Engineering · 2023
Image style transfer aims to apply artists’ painting styles to various images. Many approaches seek different purposes, but a general tendency is to increase efficiency and enable arbitrary style inputs. The state-of-art method is the adaptive convolutional network which expands the process of feature mixture into a layer-wise adjustment that superior previous work by presenting results that is more aware of detailed structures. However, the encoding process that guides the entire stylized revision is unaware of multi-scaled information. We designed an improved version of the style feature encoding procedure in our work. With the introduction of dilated convolution with a different rate, the output stylized image is better at spatial texture migration and color distribution determination. We also come up with a hybrid objective that better measures the spatial dissimilarity between content and style features.