Restora-Flow: Mask-Guided Image Restoration with Flow Matching
This work addresses image restoration challenges for applications in natural and medical imaging, representing an incremental improvement over prior flow matching techniques.
The paper tackled the problem of slow processing times and over-smoothed results in image restoration using flow matching models by introducing Restora-Flow, a training-free method that uses a degradation mask and trajectory correction, achieving superior perceptual quality and faster processing compared to existing diffusion and flow matching methods.
Flow matching has emerged as a promising generative approach that addresses the lengthy sampling times associated with state-of-the-art diffusion models and enables a more flexible trajectory design, while maintaining high-quality image generation. This capability makes it suitable as a generative prior for image restoration tasks. Although current methods leveraging flow models have shown promising results in restoration, some still suffer from long processing times or produce over-smoothed results. To address these challenges, we introduce Restora-Flow, a training-free method that guides flow matching sampling by a degradation mask and incorporates a trajectory correction mechanism to enforce consistency with degraded inputs. We evaluate our approach on both natural and medical datasets across several image restoration tasks involving a mask-based degradation, i.e., inpainting, super-resolution and denoising. We show superior perceptual quality and processing time compared to diffusion and flow matching-based reference methods.