DiTTo: Scalable Order-aware All-in-One Image Restoration Agent

arXiv:2605.30915v1 Announce Type: new Abstract: Real-world images rarely suffer from a single degradation, and the order in which degradations are removed substantially affects the final restoration quality, motivating agent-based image restoration (IR), where a vision-language model schedules a pool of pre-built restoration-experts. However, existing training-based agents require O((N^{mathbf{D}})^{2}) restoration-expert calls per image to construct the Optimal Restoration-action Trajectory Dataset (ORTD), where N^{mathbf{D}} denotes the number of degradation types in the universe mathbf{D}, and couple agent training to a fixed restoration-expert pool, preventing extension to newly introduced restoration-experts without full retraining. To overcome these efficiency and extensibility bottlenecks, we propose extbf{DiTTo}, a novel order-aware image restoration agent framework consisting of the DiTTo Simulator and the DiTTo Agent. The DiTTo Simulator combines upS-IR for single-step restoration-action simulation and AiO-IQA for per-action quality prediction, reducing ORTD construction to O(N^{mathbf{D}}) simulator calls per image; the DiTTo Agent is trained by SFT on the simulator-generated ORTD, followed by extbf{Order-aware Restoration Alignment (ORA)} that aligns degradation identification, restoration-action-ordering, and output format along independent axes. This enables extbf{plug-and-play scalable extensibility}: adding a new restoration-expert requires updating only the lightweight ORA stage. On the MiO-100 evaluation set with up to five concurrent degradations, our DiTTo Agent achieves state-of-the-art multi-degradation restoration quality among previous agent-based IR methods.

Source: arXiv cs.CV | 2026-06-01