Texture Deformation Based Generative Adversarial Networks for Face Editing
This is an incremental improvement for face editing in computer vision, addressing specific bottlenecks in image quality and training efficiency.
The paper tackles limitations in face editing such as lack of sharp details and poor identity preservation by proposing TDB-GAN, which disentangles texture for attribute and expression synthesis, resulting in sharper details and faster convergence with better performance on CelebA and RaFD datasets.
Despite the significant success in image-to-image translation and latent representation based facial attribute editing and expression synthesis, the existing approaches still have limitations in the sharpness of details, distinct image translation and identity preservation. To address these issues, we propose a Texture Deformation Based GAN, namely TDB-GAN, to disentangle texture from original image and transfers domains based on the extracted texture. The approach utilizes the texture to transfer facial attributes and expressions without the consideration of the object pose. This leads to shaper details and more distinct visual effect of the synthesized faces. In addition, it brings the faster convergence during training. The effectiveness of the proposed method is validated through extensive ablation studies. We also evaluate our approach qualitatively and quantitatively on facial attribute and facial expression synthesis. The results on both the CelebA and RaFD datasets suggest that Texture Deformation Based GAN achieves better performance.