Infrared imaging restored better under varied weather conditions
Breaking Weather-Content Coupling: Type-Severity Guided Progressive Disentanglement for All-in-One Infrared Restoration
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Infrared images often get messed up by bad weather like fog or rain, making it hard to see real thermal signals. The authors created a method that carefully separates weather effects from true heat signals, using clues about weather type and severity across an image. This approach helps keep important thermal details while removing false patterns caused by weather. It works in a step-by-step way to improve image clarity without overly darkening or hiding faint heat signals.
What this means in practice
- •For autonomous vehicle teams: Improve thermal camera images in bad weather, helping vehicles better detect real objects and obstacles.
- •For remote sensing engineers: Enhance infrared imagery clarity across different weather and regional conditions to support more accurate environmental monitoring.
Authors
Xinyao Wang, Lijun He, Zhihan Ren, Fan Li
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.