Example-Guided Style Consistent Image Synthesis from Semantic Labeling
arXiv:1906.01314
Abstract
Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style. We use the term "style" in this problem to refer to implicit characteristics of images, for example: in portraits "style" includes gender, racial identity, age, hairstyle; in full body pictures it includes clothing; in street scenes, it refers to weather and time of day and such like. A semantic label map in these cases indicates facial expression, full body pose, or scene segmentation. We propose a solution to the example-guided image synthesis problem using conditional generative adversarial networks with style consistency. Our key contributions are (i) a novel style consistency discriminator to determine whether a pair of images are consistent in style; (ii) an adaptive semantic consistency loss; and (iii) a training data sampling strategy, for synthesizing style-consistent results to the exemplar.
CVPR 2019 - Code and data - https://github.com/cxjyxxme/pix2pixSC
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Toward Multimodal Image-to-Image Translation
- FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces
- Dual Attention Network for Scene Segmentation
- Deep Photo Style Transfer
- Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
Cited by in corpus (4)
- Cross-domain Correspondence Learning for Exemplar-based Image Translation
- Dual Attention GANs for Semantic Image Synthesis
- Example-Guided Image Synthesis across Arbitrary Scenes using Masked Spatial-Channel Attention and Self-Supervision
- Example-Guided Scene Image Synthesis using Masked Spatial-Channel Attention and Patch-Based Self-Supervision