Spatial Fusion GAN for Image Synthesis
arXiv:1812.05840
Abstract
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.
Accepted to CVPR 2019
References in corpus (8)
- Conditional Generative Adversarial Nets
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
- GP-GAN: Towards Realistic High-Resolution Image Blending
- Scene Text Synthesis for Efficient and Effective Deep Network Training
- Fast Guided Filter
- Deep Painterly Harmonization
- Robust Guided Image Filtering
Cited by in corpus (5)
- Scene Text Synthesis for Efficient and Effective Deep Network Training
- End-to-End Learning of Geometric Deformations of Feature Maps for Virtual Try-On
- SwapText: Image Based Texts Transfer in Scenes
- Semantic Image Manipulation Using Scene Graphs
- Text Recognition in Real Scenarios with a Few Labeled Samples