Improving High-Frequency Detail Handling in Conditional Image Generation via Iterative Denoising in Diffusion Models

Conditional image generation has long been a critical task in computer vision. In recent years, diffusion models have surpassed Generative Adversarial Networks (GANs) in unsupervised image generation, achieving state-of-the-art results. However, challenges remain in conditional image generation, particularly in effectively preserving high-frequency details. To address this issue, we introduce a novel approach that iteratively applies denoising operations within the diffusion process to better handle high-frequency details. Our method significantly enhances the image processing capabilities of Score-based Diffusion Models (SBDMs) without requiring additional training, making it particularly effective for tasks such as image translation and cartoonization. By preserving semantic coherence while refining high-frequency details, our technique not only improves the quality of translated images but also broadens the potential applications of SBDMs across various image processing tasks.