Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis
This addresses the problem of generating photorealistic images from semantic layouts for applications like computer vision and graphics, representing an incremental improvement over existing GAN-based methods.
The paper tackles semantic image synthesis by proposing a method that predicts convolutional kernels conditioned on semantic layouts to generate images, achieving state-of-the-art results on quantitative metrics and subjective evaluations across various datasets.
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.