Weakly paired image style transfer method based on pose self-supervised generative adversarial network

Abstract

A weakly paired image style transfer method based on a pose self-supervised generative adversarial network, relating to the field of image processing. The method is suitable for style transfer of weakly paired images, different styles of pictures having certain overlap are used to perform model training of an adversarial neural network, so that the model is insensitive to poses and focuses on style learning, and therefore, in an actual application process, a source style can be converted into a target style, but a pose is kept unchanged. In addition, in the model training process of the adversarial neural network, a differentiable pose solver capable of estimating a relative pose of any two images is introduced, a phase correlation algorithm is optimized to be differentiable, and the phase correlation algorithm is embedded into an end-to-end learning network framework to achieve pose estimation.