The paper introduces SAGE-Restore, a stroke-aware restoration framework for full-page blind restoration of historical Manchu manuscripts. It first predicts patch-level repair probabilities using appearance and stroke-structural cues, then refines these into pixel-level soft gates to selectively apply restoration candidates. The authors also propose a fidelity-aware evaluation protocol and report that SAGE-Restore achieves superior recovery and fidelity metrics compared to existing methods.
arXiv:2608. 09482v1 Announce Type: cross Abstract: All-in-one image restoration is a unified low-level vision task that aims to effectively recover high-quality images from inputs degraded by various types and levels of corruption using a single model.
The paper introduces a retrieval-guided glyph-aware restoration framework for low-resource Manchu historical documents. Unlike traditional pixel-level reconstruction methods, it incorporates glyph-level structural knowledge by retrieving relevant glyph exemplars to guide the restoration process. Experiments show that this approach improves both image quality and glyph fidelity compared to existing methods.
arXiv:2607. 07051v1 Announce Type: cross Abstract: Conversational image editing requires preserving not only visible content, but also content that temporarily disappears across turns.
Degradations vary widely across images, so a practical restoration system has to handle many degradation types with one model. A recent and effective recipe adapts a large pretrained image-editing mod...
The paper introduces ImIR, a method that tunes a large pretrained image‑editing model for all‑in‑one image restoration by replacing text prompts with continuous image‑derived instructions. The approach uses a lightweight token mapper to shift the degraded image’s vision‑language embedding toward that of a clean image, enabling a single adapter to handle six restoration tasks in about three hours on one GPU. ImIR outperforms text conditioning in matched comparisons and supports task‑agnostic restoration without requiring a degradation label.
arXiv:2609.13791v1 Announce Type: new Abstract: Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom...
arXiv:2608.29037v1 Announce Type: cross Abstract: Real-world degradations such as blur, shadow, distortion, and moire patterns severely impair the document question-answering capabilities of Multimod...
SkillIR is a skill-guided framework for agentic image restoration that represents restoration experience as degradation-centered action evidence rather than full tool-use trajectories. It consolidates context-dependent action outcomes into scene-aware restoration skills, guiding one bounded action at a time within a verified residual-state loop. Experiments on synthetic and real-world multi-degradation datasets show that SkillIR improves restoration quality and enables more reliable and effective tool use.
arXiv:2605. 02814v2 Announce Type: replace-cross Abstract: Severe face degradation can remove person-specific evidence, making restoration underdetermined.
arXiv:2609.38591v1 Announce Type: new Abstract: Adapting image restoration models to a stream of new tasks without revisiting past data remains challenging due to catastrophic forgetting. In this wor...
arXiv:2606. 28112v1 Announce Type: cross Abstract: Degradation-aware prompts, conditions, and latent priors are increasingly used in image restoration, yet they are usually judged by a single endpoint: whether the restored image obtains higher PSNR.
Loop‑Mamba is a lightweight, loop‑based state‑space framework designed for restoring old photographs that suffer from multiple degradations such as scratches, cracks, fading, blur, noise, and missing regions. It models restoration as progressive state evolution, using a Semantic‑Guided Degradation Estimator to predict local degradation maps and global scores, and a Shared Structural Memory Mamba to maintain a persistent restoration state across iterations. The method employs first‑order state recursion and a multi‑directional scanning strategy to reduce gradient dilution and computational overhead, and introduces the Old Photo Damage Recovery Score (ODRS) to evaluate both degradation recovery and structural reconstruction, achieving superior performance on the SynOld benchmark.