Skip to content
Preprint

Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Models

Aug 2026 · 0 citations · 61 references
Computer Science

TL;DR

This work proposes RestoreMore, a continual capability-expansion framework that preserves the pretrained restoration model as a frozen capability anchor and learns residual expansion modules for newly arriving degradations.

Abstract

Image restoration models are typically trained with a fixed set of capabilities. When new restoration requirements emerge, existing solutions usually train additional models or jointly retrain the original model with both new and historical data. Instead of designing another restoration backbone, we investigate how a trained restorer can continually acquire new capabilities without forgetting those learned previously. We propose RestoreMore, a continual capability-expansion framework that preserves the pretrained restoration model as a frozen capability anchor and learns residual expansion modules for newly arriving degradations. RestoreMore introduces a capability-oriented bi-level routing mechanism at multiple feature stages. The first routing level identifies restoration capabilities relevant to the current input, while the second selects and combines a sparse set of complementary degradation experts. This design enables newly introduced tasks to selectively reuse historical restoration knowledge and progressively enriches the expert bank available for subsequent restoration tasks. Extensive experiments on a wide range of restoration benchmarks demonstrate that RestoreMore consistently acquires new restoration abilities while preserving and improving previously learned capabilities.

View source

Similar papers

Preprint Sep 2026

Restoring without Forgetting: Filter-Level Continual Image Restoration via Parameter-Space Integrated Gradients

Adapting image restoration models to a stream of new tasks without revisiting past data remains challenging due to catastrophic forgetting. In this work, we propose Restoring without Forgetting (RwF), a filter-level continual adaptation framework for image restoration built upon a critical observation: task-specific kn...

Xin Feng, Jin Zhao, Yi-Zhen Zhang et al. · 0 citations
Preprint Aug 2026

Restoring Without Forgetting: Continual Learning Across Image Degradations

The proposed Restoring without Forgetting (RwF) framework learns a lightweight adapter for each new degradation, eliminating forgetting by construction at a fraction of the cost of dedicated per-domain networks.

Alif Ashrafee, Bartosz Krawczyk · 0 citations
Open access Oct 2026

MDIRNET: Multi-Degradation Image Restoration Network via Deep Unfolding

Real images often exhibit unknown and mixed degradations, making restoration substantially more challenging than single-task image restoration because multiple distortion types interact within the same observation. Consequently, existing methods often rely on prior knowledge of the degradation type or separate task-spe...

T. Nadeem, Arslan Majal, Muhammad Tahir et al. · 0 citations
Preprint Aug 2026

PixRestore: Unified Image Restoration via Pixel Diffusion Transformer

PixRestore is presented, a VAE-free pixel-space Diffusion Transformer (DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining.

Ling-Chen Sun, Rong-Yuan Wu, Xiang-Tao Kong et al. · 2 citations
Preprint Sep 2026

GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration

GraLoD, a plug-and-play framework that treats restoration scale as a spatially varying and stage-dependent continuous variable, is proposed and minimal-sufficient footprint calibration (MSFC) together with structure-aware regularization (SAR) is introduced to encourage restoration-effective and spatially coherent LOD a...

Hu Gao, Li-Zhuang Ma, Yulong Chen · 0 citations
#artificial intelligence Preprint Sep 2026

Think Before You Restore: Risk-Aware Manchu Manuscript Restoration with Stroke-Guided Attention

SAGE-Restore (Stroke-Aware Gated rEstoration), a selective restoration framework that first assesses where restoration is needed and then uses this assessment to guide restoration candidate generation and pixel-level selection, is proposed.

Ming-Qiu Liang, Dongdong Wang, Si-Yang Lu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.