从事件到清晰：事件引导的扩散框架用于去雾
From Events to Clarity: The Event-Guided Diffusion Framework for Dehazing
将事件相机的高动态范围（HDR）和微秒级延迟特性引入去雾任务，通过事件引导模块将稀疏事件特征映射到扩散潜变量空间，为生成过程提供精确的结构条件，缓解语义漂移。该思路可推广到其他低层视觉任务（如低光照增强、运动去模糊）中，利用事件相机弥补RGB帧动态范围不足的问题。
原文依据 we propose an event-guided diffusion model that utilizes the strong generative priors of diffusion models to reconstruct clear images from hazy inputs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论雾霾条件下的清晰成像是一项关键任务。基于先验的方法和神经网络方法已提升了去雾效果。然而，这些方法在RGB帧上操作，而RGB帧的动态范围有限。因此，去雾仍然是一个不适定问题，可能会抹去结构和光照细节。为解决这一问题，我们首次使用事件相机进行去雾。事件相机具有更高的高动态范围（120dB vs. 60dB）和微秒级延迟，因此适合雾霾场景。在实践中，将事件中的HDR线索迁移到帧上很困难，因为真实配对数据稀缺。为此，我们提出了一种事件引导的扩散模型，利用扩散模型强大的生成先验，通过有效迁移事件中的HDR信息，从雾霾输入中重建清晰图像。具体来说，我们设计了一个事件引导模块，将稀疏的HDR事件特征（例如边缘、角点）映射到扩散潜变量空间。这种清晰的条件在生成过程中提供了精确的结构引导，提高了视觉真实感，并减少了语义漂移。对于真实世界评估，我们收集了一个在重度雾霾（AQI = 341）下同步RGB和事件传感器的无人机数据集。在两个基准和我们的数据集上的实验取得了最优结果。
英文原文摘要 1265 字符
Clear imaging under hazy conditions is a critical task. Prior-based and neural methods have improved results. However, they operate on RGB frames, which suffer from limited dynamic range. Therefore, dehazing remains ill- posed and can erase structure and illumination details. To address this, we use event cameras for dehazing for the first time. Event cameras offer much higher HDR (120dB vs. 60dB) and microsecond latency, therefore they suit hazy scenes. In practice, transferring HDR cues from events to frames is hard because real paired data are scarce. To tackle this, we propose an event-guided diffusion model that utilizes the strong generative priors of diffusion mod- els to reconstruct clear images from hazy inputs by effec- tively transferring HDR information from events. Specifi- cally, we design an event-guided module that maps sparse HDR event features, e.g., edges, corners, into the diffusion latent space. This clear conditioning provides precise struc- tural guidance during generation, improves visual realism, and reduces semantic drift. For real-world evaluation, we collect a drone dataset in heavy haze (AQI = 341) with synchronized RGB and event sensors. Experiments on two benchmarks and our dataset achieve state-of-the-art results.