Local Facial Makeup Transfer via Disentangled Representation
This work addresses the need for flexible and realistic makeup transfer in computer vision applications, offering incremental improvements over existing disentanglement methods.
The paper tackles the problem of facial makeup transfer by further disentangling makeup style into local components (lips, eyes, face), enabling control over both global and local makeup degrees and integrating makeup removal into a unified framework. The result is more realistic and accurate makeup transfer compared to state-of-the-art methods, as demonstrated in extensive experiments.
Facial makeup transfer aims to render a non-makeup face image in an arbitrary given makeup one while preserving face identity. The most advanced method separates makeup style information from face images to realize makeup transfer. However, makeup style includes several semantic clear local styles which are still entangled together. In this paper, we propose a novel unified adversarial disentangling network to further decompose face images into four independent components, i.e., personal identity, lips makeup style, eyes makeup style and face makeup style. Owing to the further disentangling of makeup style, our method can not only control the degree of global makeup style, but also flexibly regulate the degree of local makeup styles which any other approaches can't do. For makeup removal, different from other methods which regard makeup removal as the reverse process of makeup, we integrate the makeup transfer with the makeup removal into one uniform framework and obtain multiple makeup removal results. Extensive experiments have demonstrated that our approach can produce more realistic and accurate makeup transfer results compared to the state-of-the-art methods.