Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis

Abstract

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.

Accepted by NeurIPS 2019. Code is available soon at https://github.com/xh-liu/CC-FPSE

Cited by in corpus (19)

• You Only Need Adversarial Supervision for Semantic Image Synthesis
• FaR-GAN for One-Shot Face Reenactment
• COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder
• Guided Deep Decoder: Unsupervised Image Pair Fusion
• TSIT: A Simple and Versatile Framework for Image-to-Image Translation
• Diverse Semantic Image Synthesis via Probability Distribution Modeling
• Dual Attention GANs for Semantic Image Synthesis
• Learning Semantic Person Image Generation by Region-Adaptive Normalization
• Diversifying Semantic Image Synthesis and Editing via Class- and Layer-wise VAEs
• Text-to-Image Generation Grounded by Fine-Grained User Attention
• World-Consistent Video-to-Video Synthesis
• Improving Augmentation and Evaluation Schemes for Semantic Image Synthesis
• An Attention Module for Convolutional Neural Networks
• Image Synthesis via Semantic Composition
• Realistic Image Synthesis with Configurable 3D Scene Layouts
• Human-In-The-Loop Document Layout Analysis
• Deep Image Synthesis from Intuitive User Input: A Review and Perspectives
• Stay Positive: Non-Negative Image Synthesis for Augmented Reality
• Collaging Class-specific GANs for Semantic Image Synthesis