Sym-parameterized Dynamic Inference for Mixed-Domain Image Translation
This addresses a limitation in image-to-image translation for creating images in novel mixed domains, though it appears incremental as it builds on existing multi-domain methods by extending the concept to loss areas.
The paper tackles the problem of generating images in mixed domains without requiring datasets for those specific target domains, achieving the ability to translate images to any mixed-domain combination, such as 30% Van Gogh, 20% Monet, and 40% snowy, without ground truths.
Recent advances in image-to-image translation have led to some ways to generate multiple domain images through a single network. However, there is still a limit in creating an image of a target domain without a dataset on it. We propose a method that expands the concept of `multi-domain' from data to the loss area and learns the combined characteristics of each domain to dynamically infer translations of images in mixed domains. First, we introduce Sym-parameter and its learning method for variously mixed losses while synchronizing them with input conditions. Then, we propose Sym-parameterized Generative Network (SGN) which is empirically confirmed of learning mixed characteristics of various data and losses, and translating images to any mixed-domain without ground truths, such as 30% Van Gogh and 20% Monet and 40% snowy.