Semantic Image Synthesis via Diffusion Models

TL;DR

This paper introduces a novel diffusion model framework for semantic image synthesis that leverages separate processing of semantic layouts and noisy images, achieving state-of-the-art results in image quality and diversity.

Contribution

The proposed framework processes semantic layouts and noisy images differently using multi-layer spatially-adaptive normalization, and employs classifier-free guidance for improved synthesis quality.

Findings

Achieves state-of-the-art FID scores on benchmark datasets.

Demonstrates higher diversity in generated images compared to previous methods.

Effective semantic interpretability in image synthesis.

Abstract

Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks compared with Generative Adversarial Nets (GANs). Recent work on semantic image synthesis mainly follows the de facto GAN-based approaches, which may lead to unsatisfactory quality or diversity of generated images. In this paper, we propose a novel framework based on DDPM for semantic image synthesis. Unlike previous conditional diffusion model directly feeds the semantic layout and noisy image as input to a U-Net structure, which may not fully leverage the information in the input semantic mask, our framework processes semantic layout and noisy image differently. It feeds noisy image to the encoder of the U-Net structure while the semantic layout to the decoder by multi-layer spatially-adaptive normalization operators. To further improve the generation quality and semantic interpretability in semantic image synthesis, we introduce the classifier-free guidance sampling strategy, which acknowledge the scores of an unconditional model for sampling process. Extensive experiments on four benchmark datasets demonstrate the effectiveness of our proposed method, achieving state-of-the-art performance in terms of fidelity (FID) and diversity (LPIPS). Our code and pretrained models are available at https://github.com/WeilunWang/semantic-diffusion-model.