Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding
By: S M A Sharif , Abdur Rehman , Fayaz Ali Dharejo and more
Potential Business Impact:
Cleans blurry pictures from rain, fog, or dark.
Real-world images often suffer from spatially diverse degradations such as haze, rain, snow, and low-light, significantly impacting visual quality and downstream vision tasks. Existing all-in-one restoration (AIR) approaches either depend on external text prompts or embed hand-crafted architectural priors (e.g., frequency heuristics); both impose discrete, brittle assumptions that weaken generalization to unseen or mixed degradations. To address this limitation, we propose to reframe AIR as learned latent prior inference, where degradation-aware representations are automatically inferred from the input without explicit task cues. Based on latent priors, we formulate AIR as a structured reasoning paradigm: (1) which features to route (adaptive feature selection), (2) where to restore (spatial localization), and (3) what to restore (degradation semantics). We design a lightweight decoding module that efficiently leverages these latent encoded cues for spatially-adaptive restoration. Extensive experiments across six common degradation tasks, five compound settings, and previously unseen degradations demonstrate that our method outperforms state-of-the-art (SOTA) approaches, achieving an average PSNR improvement of 1.68 dB while being three times more efficient.
Similar Papers
Any Image Restoration via Efficient Spatial-Frequency Degradation Adaptation
CV and Pattern Recognition
Fixes blurry pictures with one smart tool.
Multi-Agent Image Restoration
CV and Pattern Recognition
Fixes blurry pictures by fixing different problems.
TAP: Parameter-efficient Task-Aware Prompting for Adverse Weather Removal
CV and Pattern Recognition
Cleans blurry pictures from bad weather.