Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
This addresses a specific bottleneck in generative models for computer vision researchers, offering an incremental improvement to existing methods.
The paper tackles the problem of mode collapse in multi-mapping image-to-image translation caused by latent code injection and normalization strategies, proposing central biasing normalization to improve quality and diversity in models like StarGAN, BicycleGAN, and pix2pix.
Recent advances in image-to-image translation have seen a rise in approaches generating diverse images through a single network. To indicate the target domain for a one-to-many mapping, the latent code is injected into the generator network. However, we found that the injection method leads to mode collapse because of normalization strategies. Existing normalization strategies might either cause the inconsistency of feature distribution or eliminate the effect of the latent code. To solve these problems, we propose the consistency within diversity criteria for designing the multi-mapping model. Based on the criteria, we propose central biasing normalization to inject the latent code information. Experiments show that our method can improve the quality and diversity of existing image-to-image translation models, such as StarGAN, BicycleGAN, and pix2pix.