arXiv · 2611.22222
ExplicitIR: Explicit Spatial Policy Fields for All-in-One Image Restoration
Abstract
All-in-one image restoration aims to recover clean images blindly from inputs with various degradation types and levels using a single model. However, the adaptation policy in most existing methods remains implicitly encoded in feature representations, leaving the restoration decision neither explicitly represented nor independently controllable. Since real-world degradations vary spatially, applying uniform updates across the entire image leads to over-smoothing of clean areas and under-correction of localized degradations. To address these limitations, we present ExplicitIR, which represents the restoration policy as two explicit per-pixel fields: Budget, which determines where and how strongly to update, and Style, which selects between narrow and wide context windows. Specifically, ExplicitIR incorporates a Spatial Policy Estimator (SPE) to predict these fields, explicitly representing the restoration policy and capturing spatially-varying degradations, which are then applied by Policy-Adaptive Decoder Blocks (PADB) through adaptive fusion of narrow- and wide-window responses, enabling independent control and precise local modulation. This design enables spatially-adaptive restoration in a single forward pass, without requiring task labels, prompts, or test-time degradation estimators. Extensive experiments on three-task and five-task benchmarks demonstrate that ExplicitIR achieves performance competitive with the strongest all-in-one baselines.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Dezhi Zhang, Shangrong Yang, Yudong Liang, Wenjian Wang. 2026-11-17. ExplicitIR: Explicit Spatial Policy Fields for All-in-One Image Restoration. https://searcharxiv.com/abs/2611.22222
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.