Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image RestorationSimilar Papers 제목 키워드 기반
Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities
Cross-lingual continual pre-training of large language models (LLMs) initially trained on English corpus allows us to leverage the vast amount of English language resources and reduce the pre-training cost. In this study…
Question AnsweringMaintain Plasticity in Long-timescale Continual Test-time Adaptation
Continual test-time domain adaptation (CTTA) aims to adjust pre-trained source models to perform well over time across non-stationary target environments. While previous methods have made considerable efforts to optimize…
Domain AdaptationTest-time AdaptationCRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning
Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-world deployment demands continuous capability expansion, making Mul…
Similarity-based context aware continual learning for spiking neural networks
Biological brains have the capability to adaptively coordinate relevant neuronal populations based on the task context to learn continuously changing tasks in real-world environments. However, existing spiking neural net…
class-incremental learningClass Incremental LearningContinual LearningIncremental LearningLargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models
Online task-free continual learning (TFCL) requires intelligent agents to sequentially accumulate knowledge from an unbounded, non-stationary data stream under strict single-pass constraints and without any explicit task…
Continual Learning