Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding

ICLR 2026 Conference Submission342 Authors

Keywords: all-in-one restoration, latent encoding, prompt-free AIR, image enhancement

TL;DR: We propose reframing all-in-one restoration using latent priors and structural reasoning cues to effectively handle both seen and unseen degradations.

Abstract: 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. Code will be released upon publication.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 342