RetouchFormer: Semi-supervised High-Quality Face Retouching Transformer with Prior-Based Selective Self-Attention

Face retouching is to beautify a face image, while preserving the image content as much as possible. It is a promising yet challenging task to remove face imperfections and fill with normal skin. Generic image enhancement methods are hampered by the lack of imperfection localization, which typically results in incomplete removal of blemishes at large scales. To address this issue, we propose a transformer-based approach, RetouchFormer, which simultaneously identifies imperfections and synthesizes realistic content in the corresponding regions. Specifically, we learn a latent dictionary to capture clean face priors, and predict the imperfection regions via a reconstruction-oriented localization module. Also based on this, we can realize face retouching by explicitly suppressing imperfections in selective self-attention computation, such that local content will be synthesized from normal skin. On the other hand, multi-scale feature tokens lead to increased flexibility in dealing with the imperfections at various scales. The design elements bring greater effectiveness and efficiency. RetouchFormer outperforms the advanced face retouching methods and synthesizes clean face images with high fidelity in our list of extensive experiments performed. Copyright © 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.