Injecting-Diffusion: Inject Domain-Independent Contents into Diffusion Models for Unpaired Image-to-Image Translation

Diffusion models have shown remarkable performance in the task of image synthesis. However, we notice that existing methods fail to preserve domain-independent contents of the input images, making it challenging for unpaired image-to-image translation. To address this issue, we proposed a diffusion model for domain-independent content injecting. We propose a domain-independent content extractor to obtain domain-independent contents from the source domain. After that, we inject the extracted contents into the diffusion model and fuse them with domain-specific appearances of the target domain through our proposed cross-domain attention mechanism. The qualitative and quantitative experiments demonstrate that our proposed method can generate high-fidelity images of the target domain while preserving domain-independent contents of the source domain.