Example-Guided Style-Consistent Image Synthesis From Semantic Labeling
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. We demonstrate the efficiency of our method on face, dance and street view synthesis tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationScene SegmentationSimilar Papers 제목 키워드 기반
Example-Guided Style Consistent Image Synthesis from Semantic Labeling
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 ex…
Image GenerationScene SegmentationFrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchronized GANs
Coarse building mass models are now routinely generated at scales ranging from individual buildings through to whole cities. For example, they can be abstracted from raw measurements, generated procedurally, or created m…
Texture SynthesisBlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation
Generative Adversarial Networks (GANs) have made a dramatic leap in high-fidelity image synthesis and stylized face generation. Recently, a layer-swapping mechanism has been developed to improve the stylization performan…
DiversityFace GenerationImage GenerationMore Control for Free! Image Synthesis with Semantic Diffusion Guidance
Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from a reference image. Recently, denoising diffusion probabilistic models have been shown to generate more real…
continuous-controlContinuous ControlDenoisingImage GenerationExample-Guided Image Synthesis using Masked Spatial-Channel Attention and Self-Supervision
Example-guided image synthesis has recently been attempted to synthesize an image from a semantic label map and an exemplary image. In the task, the additional exemplar image provides the style guidance that controls the…
Image GenerationSpatial Interpolation