用于端到端真实世界图像去雾的骨干无关扰动诱导不确定性学习

中文摘要 AI 辅助

真实世界的成对图像去雾具有挑战性，因为雾的退化在空间上不均匀、依赖光照且物理上模糊。现有端到端恢复网络将去雾视为确定性映射，未充分探索退化特征、雾先验和跨域负样本中的不确定性。本文提出骨干无关扰动诱导不确定性学习（BPUL）框架，引入可学习扰动诱导不确定性调制器估计特征敏感性，开发先验信息不确定性引导重建模块利用先验重建模糊观测并加强退化一致性，还提出双空间域多样化分布感知对比损失进行正则化。在五个真实世界成对基准上的实验表明，BPUL持续改进多个代表性骨干，推理时仅保留LPUM，带来显著恢复增益且推理开销小。

英文摘要

Real-world paired image dehazing remains challenging because haze degradation is spatially non-uniform, illumination-dependent, and physically ambiguous even when haze-free references are available. Existing end-to-end restoration networks usually learn a deterministic mapping from a hazy observation to a clean target, while degradation-sensitive feature responses, reverse haze-formation consistency, and cross-domain negative structure remain insufficiently exploited. In this paper, we propose Backbone-Agnostic Stochastic Perturbation Learning (BSPL), a plug-and-play framework for end-to-end real-world image dehazing. BSPL first introduces a Learnable Stochastic Perturbation Modulator (LSPM), which learns input-conditioned channel-wise and spatial-wise perturbation distributions and converts the resulting feature-response discrepancies into adaptive modulation weights. It then develops a Prior-informed Perturbation-guided Reconstruction Module (PPRM), which reuses the learned bottleneck perturbations together with transmission and atmospheric-light priors to reconstruct the hazy observation from the restored result and enforce degradation consistency. Furthermore, we propose a Dual-space Domain-diversified Distribution-aware Contrastive Loss ($D^3$CL) to regularize both clean restoration and hazy reconstruction spaces with real-world and synthetic negatives. Experiments on five real-world paired benchmarks show that BSPL consistently improves multiple representative backbones with only marginal additional inference overhead.

发表机构

• Bingcai Wei（独立研究者）

机构由 AI 辅助整理，请以论文原文为准。