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

• URL: http://arxiv.org/abs/2608.30305v1
• Date: Mon, 31 Aug 2026 06:19:58 GMT
• Title: Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Models
• Abstract summary: We investigate how a trained restorer can continually acquire new capabilities without forgetting those learned previously.<n>We propose RestoreMore, a continual capability-expansion framework.<n>We show that RestoreMore consistently acquires new restoration abilities while preserving and improving previously learned capabilities.
• Score: 54.85451496831771
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents [54.85451496831771]
  Causal-AgentIR is a hierarchical multi-agent framework with self-evolving causal memory for collective image restoration intelligence.<n>It organizes degradation patterns, image regions, restoration tools, actions, quality changes, and user preferences into a structured causal memory graph.<n>This graph supports graph-based retrieval and multi-hop causal reasoning, enabling agents to infer how specific restoration operations or tool sequences affect restoration quality under different degradation conditions.
  arXiv  Detail & Related papers  (2026-07-23T09:59:44Z)
• Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration [84.3817904120563]
  Image restoration aims to recover high quality images from inputs degraded by various factors, such as adverse weather, blur, or low light.<n>We propose RAR, a Restore, Assess and Repeat process, that integrates Image Quality Assessment (IQA) and Image Restoration (IR) into a unified framework.<n> Specifically, we introduce a restoration process that operates entirely in the latent domain to jointly perform degradation identification, image restoration, and quality verification.
  arXiv  Detail & Related papers  (2026-03-27T13:13:44Z)
• UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration [20.447922377156143]
  Universal image restoration aims to recover clean images from arbitrary real-world degradations.<n>Existing all-in-one restoration networks do not scale to multiple degradations.<n>We introduce a unified inference pipeline with a mixture-of-experts architecture that decomposes restoration knowledge across specialized task-adaptable experts.
  arXiv  Detail & Related papers  (2026-03-08T01:35:54Z)
• From Physical Degradation Models to Task-Aware All-in-One Image Restoration [44.45223512440674]
  All-in-one image restoration aims to adaptively handle multiple restoration tasks with a single trained model.<n>We adopt a physical degradation modeling perspective and predict a task-aware inverse degradation operator for efficient all-in-one image restoration.
  arXiv  Detail & Related papers  (2026-01-15T08:47:10Z)
• Sharing the Learned Knowledge-base to Estimate Convolutional Filter Parameters for Continual Image Restoration [7.116541784404478]
  We propose a simple modification of the convolution layer to adapt the knowledge from previous restoration tasks without touching the main backbone architecture.<n>Unlike other approaches, we demonstrate that our model can increase the number of trainable parameters without significantly increasing computational overhead or inference time.
  arXiv  Detail & Related papers  (2025-11-07T16:52:42Z)
• UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity [79.90839080916913]
  We present our UniRestorer with improved restoration performance.<n>Specifically, we perform hierarchical clustering on degradation space, and train a multi-granularity mixture-of-experts (MoE) restoration model.<n>In contrast to existing degradation-agnostic and -aware methods, UniRestorer can leverage degradation estimation to benefit degradation specific restoration.
  arXiv  Detail & Related papers  (2024-12-28T14:09:08Z)
• Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild [57.06779516541574]
  SUPIR (Scaling-UP Image Restoration) is a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up. We collect a dataset comprising 20 million high-resolution, high-quality images for model training, each enriched with descriptive text annotations.
  arXiv  Detail & Related papers  (2024-01-24T17:58:07Z)
• SPIRE: Semantic Prompt-Driven Image Restoration [66.26165625929747]
  We develop SPIRE, a Semantic and restoration Prompt-driven Image Restoration framework. Our approach is the first framework that supports fine-level instruction through language-based quantitative specification of the restoration strength. Our experiments demonstrate the superior restoration performance of SPIRE compared to the state of the arts.
  arXiv  Detail & Related papers  (2023-12-18T17:02:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.