Hierarchy Composition GAN for High-fidelity Image Synthesis
This addresses the challenge of high-fidelity image synthesis for applications such as scene text generation and portrait editing, representing a novel integration rather than an incremental step.
The paper tackles the problem of image synthesis artifacts by introducing a Hierarchical Composition GAN (HIC-GAN) that integrates geometry and appearance domains into an end-to-end network, achieving superior realism with qualitative and quantitative improvements in tasks like scene text synthesis and portrait editing.
Despite the rapid progress of generative adversarial networks (GANs) in image synthesis in recent years, the existing image synthesis approaches work in either geometry domain or appearance domain alone which often introduces various synthesis artifacts. This paper presents an innovative Hierarchical Composition GAN (HIC-GAN) that incorporates image synthesis in geometry and appearance domains into an end-to-end trainable network and achieves superior synthesis realism in both domains simultaneously. We design an innovative hierarchical composition mechanism that is capable of learning realistic composition geometry and handling occlusions while multiple foreground objects are involved in image composition. In addition, we introduce a novel attention mask mechanism that guides to adapt the appearance of foreground objects which also helps to provide better training reference for learning in geometry domain. Extensive experiments on scene text image synthesis, portrait editing and indoor rendering tasks show that the proposed HIC-GAN achieves superior synthesis performance qualitatively and quantitatively.