Problem
Research questions and friction points this paper is trying to address.
Infrared Restoration
Weather-Content Coupling
Degradation Severity
Thermal Structures
Artifacts
Breaking Weather-Content Coupling: Type-Severity Guided Progressive Disentanglement for All-in-One Infrared Restoration
🤖 AI Summary
为解决红外图像中天气引起的虚假结构与真实热结构纠缠问题，提出了一种基于类型-严重度引导的渐进解耦网络TSGPD-IR。
📝 Abstract
Infrared (IR) imaging is crucial for autonomous driving, remote sensing, and other perception tasks. However, adverse weather may introduce fake structural responses that are entangled with real thermal structures. Existing IR restoration methods are typically designed for a single degradation type or directly reconstruct from degradation-entangled representations. Consequently, they struggle to distinguish intrinsic thermal structures from weather-induced fake responses and to accommodate spatially varying degradation severity, leading to artifacts or the over-suppression of weak but meaningful thermal responses. To address these issues, we propose TSGPD-IR, a type-severity guided progressive disentanglement network for all-in-one infrared restoration that factorizes restoration guidance into task-level weather semantics and region-level degradation severity. Specifically, a Weather and Semantic Co-Guided Multi-Level Prompt Generation Module combines global weather semantics with stage-wise local features to generate adaptive prompts that progressively suppress degradation-induced responses while preserving intrinsic thermal structures. To complement global weather semantics with spatial restoration control, a Proxy-Supervised Regional Degradation Estimator derives severity supervision without manual annotations and predicts spatially varying degradation priors. Guided by these cues, a Multi-Source Collaborative Expert Selection Strategy uses a shared branch to preserve weather-invariant thermal structures and hierarchical routing to select weather-specific expert pools and severity-compatible regional experts. This design progressively separates degradation interference from genuine thermal content and enables region-adaptive restoration, reducing both residual artifacts and over-suppression.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Progressive Disentanglement
Weather Semantics
Degradation Severity
Multi-Level Prompt Generation
Regional Degradation Estimator
🔎 Similar Papers
No similar papers found.
