Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis

TL;DR

This paper introduces RESAIL, a novel normalization module that uses pixel-level guidance from retrieved patches or distorted ground-truth images to improve the quality of semantic image synthesis, reducing blurriness.

Contribution

The paper proposes RESAIL, a retrieval-based spatially adaptive normalization method that incorporates fine-grained, pixel-level guidance for enhanced semantic image synthesis.

Findings

RESAIL outperforms state-of-the-art methods on multiple datasets.

Using retrieved patches improves visual quality and reduces blurriness.

Distorted ground-truth images as guidance further enhance synthesis results.

Abstract

Semantic image synthesis is a challenging task with many practical applications. Albeit remarkable progress has been made in semantic image synthesis with spatially-adaptive normalization and existing methods normalize the feature activations under the coarse-level guidance (e.g., semantic class). However, different parts of a semantic object (e.g., wheel and window of car) are quite different in structures and textures, making blurry synthesis results usually inevitable due to the missing of fine-grained guidance. In this paper, we propose a novel normalization module, termed as REtrieval-based Spatially AdaptIve normaLization (RESAIL), for introducing pixel level fine-grained guidance to the normalization architecture. Specifically, we first present a retrieval paradigm by finding a content patch of the same semantic class from training set with the most similar shape to each test semantic mask. Then, RESAIL is presented to use the retrieved patch for guiding the feature normalization of corresponding region, and can provide pixel level fine-grained guidance, thereby greatly mitigating blurry synthesis results. Moreover, distorted ground-truth images are also utilized as alternatives of retrieval-based guidance for feature normalization, further benefiting model training and improving visual quality of generated images. Experiments on several challenging datasets show that our RESAIL performs favorably against state-of-the-arts in terms of quantitative metrics, visual quality, and subjective evaluation. The source code and pre-trained models will be publicly available.