Spatial Fusion GAN for Image Synthesis
This work addresses the challenge of generating realistic images for applications such as training recognition models and enhancing portraits, representing an incremental improvement by integrating existing synthesis approaches.
The paper tackles the problem of realistic image synthesis by addressing both geometry and appearance spaces, presenting Spatial Fusion GAN (SF-GAN) which combines geometry and appearance synthesizers to achieve superior results in tasks like scene text image synthesis and portrait accessory matching, as demonstrated through qualitative and quantitative comparisons with state-of-the-art methods.
Recent advances in generative adversarial networks (GANs) have shown great potentials in realistic image synthesis whereas most existing works address synthesis realism in either appearance space or geometry space but few in both. This paper presents an innovative Spatial Fusion GAN (SF-GAN) that combines a geometry synthesizer and an appearance synthesizer to achieve synthesis realism in both geometry and appearance spaces. The geometry synthesizer learns contextual geometries of background images and transforms and places foreground objects into the background images unanimously. The appearance synthesizer adjusts the color, brightness and styles of the foreground objects and embeds them into background images harmoniously, where a guided filter is introduced for detail preserving. The two synthesizers are inter-connected as mutual references which can be trained end-to-end without supervision. The SF-GAN has been evaluated in two tasks: (1) realistic scene text image synthesis for training better recognition models; (2) glass and hat wearing for realistic matching glasses and hats with real portraits. Qualitative and quantitative comparisons with the state-of-the-art demonstrate the superiority of the proposed SF-GAN.