The reviewed record of science sign in
Pith

arxiv: 2204.02854 · v1 · pith:WCLTDIRZ · submitted 2022-04-06 · cs.CV

Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WCLTDIRZrecord.jsonopen to challenge →

classification cs.CV
keywords normalizationsemanticguidancesynthesisfeaturefine-grainedimageresail
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.