Semantically Multi-modal Image Synthesis
This work addresses the limitation of previous methods in handling many classes for semantically multi-modal image synthesis, offering incremental improvements in controllability and quality.
The paper tackles the problem of generating diverse images from semantic labels, especially for datasets with many classes, by proposing GroupDNet, which improves controllability and yields high-quality results, as demonstrated on challenging datasets.
In this paper, we focus on semantically multi-modal image synthesis (SMIS) task, namely, generating multi-modal images at the semantic level. Previous work seeks to use multiple class-specific generators, constraining its usage in datasets with a small number of classes. We instead propose a novel Group Decreasing Network (GroupDNet) that leverages group convolutions in the generator and progressively decreases the group numbers of the convolutions in the decoder. Consequently, GroupDNet is armed with much more controllability on translating semantic labels to natural images and has plausible high-quality yields for datasets with many classes. Experiments on several challenging datasets demonstrate the superiority of GroupDNet on performing the SMIS task. We also show that GroupDNet is capable of performing a wide range of interesting synthesis applications. Codes and models are available at: https://github.com/Seanseattle/SMIS.