SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

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 mod

Read original source ↗ Open in workspace

recordType

paper

region

Global