Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptation
This work addresses the domain adaptation problem for vision systems in adverse conditions where labeled real data is scarce, offering an incremental improvement over existing style transfer approaches.
The paper tackles the problem of semantic segmentation models performing poorly on real-world images when trained on synthetic data due to domain gaps, by proposing diffusion-based style transfer methods (CACTI and CACTIF) that improve image quality with lower FID scores and better content preservation in experiments using GTA5 as source and Cityscapes/ACDC as target domains.
Semantic segmentation models trained on synthetic data often perform poorly on real-world images due to domain gaps, particularly in adverse conditions where labeled data is scarce. Yet, recent foundation models enable to generate realistic images without any training. This paper proposes to leverage such diffusion models to improve the performance of vision models when learned on synthetic data. We introduce two novel techniques for semantically consistent style transfer using diffusion models: Class-wise Adaptive Instance Normalization and Cross-Attention (CACTI) and its extension with selective attention Filtering (CACTIF). CACTI applies statistical normalization selectively based on semantic classes, while CACTIF further filters cross-attention maps based on feature similarity, preventing artifacts in regions with weak cross-attention correspondences. Our methods transfer style characteristics while preserving semantic boundaries and structural coherence, unlike approaches that apply global transformations or generate content without constraints. Experiments using GTA5 as source and Cityscapes/ACDC as target domains show that our approach produces higher quality images with lower FID scores and better content preservation. Our work demonstrates that class-aware diffusion-based style transfer effectively bridges the synthetic-to-real domain gap even with minimal target domain data, advancing robust perception systems for challenging real-world applications. The source code is available at: https://github.com/echigot/cactif.