Cycle-Consistent Adversarial Networks and Fast Adaptive Bi-dimensional Empirical Mode Decomposition for Style Transfer

Abstract

Recently, research endeavors have shown the potentiality of Cycle-Consistent Adversarial Networks (CycleGAN) in style transfer. In Cycle-Consistent Adversarial Networks, the consistency loss is introduced to measure the difference between the original images and the reconstructed in both directions, forward and backward. In this work, the combination of Cycle-Consistent Adversarial Networks with Fast and Adaptive Bidimensional Empirical Mode Decomposition (FABEMD) is proposed to perform style transfer on images. In the proposed approach the cycleconsistency loss is modified to include the differences between the extracted Intrinsic Mode Functions (BIMFs) images. Instead of an estimation of pixel-to-pixel difference between the produced and input images, the FABEMD is applied and the extracted BIMFs are involved in the computation of the total cycle loss. This method enriches the computation of the total loss in a content-tocontent and style-to-style comparison by connecting the spatial information to the frequency components. The experimental results reveal that the proposed method is efficient and produces qualitative results comparable to state-of-the-art methods.

V4Design: Intelligent Analysis and Integration of Multimedia Content for Creative Industries

“…The Texturing component applies a style from a user selected image (such as a painting or a building of a specific architecture) onto an automatically generated 3D model's texture, thereby creating a new textured asset [2].…”