Landmark Assisted CycleGAN for Cartoon Face Generation
This work addresses the challenge of cross-domain image translation for cartoon face generation, which is incremental as it builds upon existing CycleGAN methods by adding landmark guidance.
The paper tackles the problem of generating cartoon faces from real faces using unpaired training data by proposing a landmark-assisted CycleGAN that incorporates face landmarks to define consistency loss and guide local discriminator training, resulting in high-quality cartoon faces that are largely indistinguishable from artist-drawn ones and significantly improving state-of-the-art performance.
In this paper, we are interested in generating an cartoon face of a person by using unpaired training data between real faces and cartoon ones. A major challenge of this task is that the structures of real and cartoon faces are in two different domains, whose appearance differs greatly from each other. Without explicit correspondence, it is difficult to generate a high quality cartoon face that captures the essential facial features of a person. In order to solve this problem, we propose landmark assisted CycleGAN, which utilizes face landmarks to define landmark consistency loss and to guide the training of local discriminator in CycleGAN. To enforce structural consistency in landmarks, we utilize the conditional generator and discriminator. Our approach is capable to generate high-quality cartoon faces even indistinguishable from those drawn by artists and largely improves state-of-the-art.