Expandable, Compressible, Mineable: Open-World Thermal Image Restoration

TL;DR

This paper introduces ECMRNet, a continual learning framework for open-world thermal image restoration that adaptively expands, compresses, and reuses model components to handle evolving degradations efficiently.

Contribution

ECMRNet is a novel open-world TIR restoration network that unifies continual degradation learning with an expand-compress-mine cycle, enabling effective adaptation and model compression.

Findings

ECMRNet outperforms existing methods on diverse degradation types.

It achieves superior restoration with fewer parameters and lower computational cost.

Structural Entropy Pruning effectively compresses the model without performance loss.

Abstract

In open-world settings, thermal infrared (TIR) image degradations continuously emerge and evolve, while most existing all-in-one restoration methods are built on a closed-set assumption and struggle to continually adapt to novel degradations. To address this, we propose ECMRNet, an Expandable, Compressible, and Mineable Restoration Network for open-world TIR restoration from a continual learning perspective. Conceptually, ECMRNet unifies continual degradation learning as an "expand-compress-mine" closed-loop process, enabling sustained adaptation to new degradations with controllable evolution. Structurally, ECMRNet decomposes intermediate representations into group-isolated subspaces, and achieves strict parameter isolation and fast adaptation to new degradations by freezing historical groups and isomorphically expanding new ones. To curb model growth as tasks accumulate, we present Structural Entropy Pruning, which identifies and removes redundant channel groups via two-dimensional structural entropy minimization, achieving information contribution-driven adaptive compression. Moreover, we design a Sub-degradation Knowledge Mining Module that dynamically retrieves and recombines transferable components from historical representations to improve restoration under compound degradations. Experimental results demonstrate that ECMRNet achieves superior overall performance across diverse single and compound degradations while using fewer parameters and lower computational cost. The source code is available at https://github.com/Kust-lp/ECMRNet.