RestoRect: Degraded Image Restoration via Latent Rectified Flow & Feature Distillation

arXiv:2509.23480v3 Announce Type: replace Abstract: Current approaches for restoration of degraded images face a trade-off: high-performance models are slow for practical use, while fast models produce poor results. Knowledge distillation transfers teacher knowledge to students, but existing static feature matching methods cannot capture how modern transformer architectures dynamically generate features. We propose a novel Latent Rectified Flow Feature Distillation method for restoring degraded images called extbf{'RestoRect'}. We apply rectified flow to reformulate feature distillation as a generative process where students learn to synthesize teacher-quality features through learnable trajectories in latent space. Our framework combines Retinex decomposition with learnable anisotropic diffusion constraints, and trigonometric color space polarization. We introduce a Feature Layer Extraction loss for robust knowledge transfer between different network architectures through cross-normalized transformer feature alignment with percentile-based outlier detection. RestoRect achieves better training stability, and faster convergence and inference while preserving restoration quality, demonstrating superior results across 15 image restoration datasets, covering 4 tasks, on 10 metrics against baselines.

Related

• LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer
• MirrorDistill: Illumination-Aware Latent Distillation for Efficient Low-Light Restoration
• DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models
• Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models
• MixFlow: Mixed Source Distributions Improve Rectified Flows

Source: arXiv cs.CV | 2026-10-20