Problem
Research questions and friction points this paper is trying to address.
adverse weather
image restoration
heterogeneous degradations
weather-agnostic global aggregation
cross-scale fusion
Uncertainty-Guided Adverse Weather Restoration via Gated Transformer Network
🤖 AI Summary
为解决因天气引起的图像退化问题，提出UAR-Net，通过集成门控变换器和多尺度跳跃连接，并采用不确定性感知的精细化头来处理异质性退化。
📝 Abstract
Restoring images degraded by adverse weather remains challenging due to spatially heterogeneous degradations. Many existing weather-specific restoration models rely on weather-agnostic global aggregation, naive cross-scale fusion, and deterministic objectives, which struggle to handle heterogeneous degradations in all-in-one adverse-weather settings. To address these limitations, we propose an Uncertainty-guided Adverse-weather Restoration Network (UAR-Net), a weather-specific AiO framework that integrates a gated transformer with balanced multi-scale skip connections. Specifically, we employ Gated Dual-scale Transformer Blocks (GDTB) to jointly model selective global interactions and multi-scale local structures, a progressive Balanced Multi-scale Skip Connection (BMSC) for balanced multi-scale feature integration, and an Uncertainty-Aware Refinement Head (URH) that performs artifact removal, detail enhancement, and predictive uncertainty estimation. The model is supervised by a Brightness-Aware Energy Loss (BAE-Loss) to encourage accurate reconstruction with well-calibrated uncertainty. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple adverse-weather benchmarks. The codes will open source upon acceptance.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Gated Dual-scale Transformer Blocks (GDTB)
Balanced Multi-scale Skip Connection (BMSC)
Uncertainty-Aware Refinement Head (URH)
Brightness-Aware Energy Loss (BAE-Loss)
🔎 Similar Papers
No similar papers found.
