SDIT: Scalable and Diverse Cross-domain Image Translation
This addresses a limitation in image-to-image translation for researchers and practitioners, but it is incremental as it combines existing properties into a single method.
The paper tackled the problem of combining diverse outputs and scalable image transfer in image-to-image translation, proposing SDIT which achieved competitive performance on face mapping and other datasets.
Recently, image-to-image translation research has witnessed remarkable progress. Although current approaches successfully generate diverse outputs or perform scalable image transfer, these properties have not been combined into a single method. To address this limitation, we propose SDIT: Scalable and Diverse image-to-image translation. These properties are combined into a single generator. The diversity is determined by a latent variable which is randomly sampled from a normal distribution. The scalability is obtained by conditioning the network on the domain attributes. Additionally, we also exploit an attention mechanism that permits the generator to focus on the domain-specific attribute. We empirically demonstrate the performance of the proposed method on face mapping and other datasets beyond faces.