Timezone: »

 
Poster
Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis
Xihui Liu · Guojun Yin · Jing Shao · Xiaogang Wang · hongsheng Li

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #68
in Applications -- Computer Vision »

Semantic image synthesis aims at generating photorealistic images from semantic layouts. Previous approaches with conditional generative adversarial networks (GAN) show state-of-the-art performance on this task, which either feed the semantic label maps as inputs to the generator, or use them to modulate the activations in normalization layers via affine transformations. We argue that convolutional kernels in the generator should be aware of the distinct semantic labels at different locations when generating images. In order to better exploit the semantic layout for the image generator, we propose to predict convolutional kernels conditioned on the semantic label map to generate the intermediate feature maps from the noise maps and eventually generate the images. Moreover, we propose a feature pyramid semantics-embedding discriminator, which is more effective in enhancing fine details and semantic alignments between the generated images and the input semantic layouts than previous multi-scale discriminators. We achieve state-of-the-art results on both quantitative metrics and subjective evaluation on various semantic segmentation datasets, demonstrating the effectiveness of our approach.

Keywords: Deep Learning -> Generative Models · Applications -> Computer Vision; Deep Learning -> Adversarial Networks

Author Information

Xihui Liu (The Chinese University of Hong Kong)
Guojun Yin (University of Science and Technology of China)
Jing Shao (Sensetime)
Xiaogang Wang (The Chinese University of Hong Kong)
hongsheng Li (cuhk)

More from the Same Authors