Unveiling the dense correspondence under the haze layer remains a challenging task, since the scattering effects result in less distinctive image features. Contrarily, dehazing is often confused by the airlight-albedo ambiguity which cannot be resolved independently at each pixel. In this paper, we introduce a deep convolutional neural network that simultaneously estimates a disparity and clear image from a hazy stereo image pair. Both tasks are synergistically formulated by fusing depth information from the matching cost and haze transmission. To learn the optimal fusion of depth-related features, we present a novel encoder-decoder architecture that extends the core idea of attention mechanism to the simultaneous stereo matching and dehazing. As a result, our method estimates high-quality disparity for the stereo images in scattering media, and produces appearance images with enhanced visibility. Finally, we further propose an effective strategy for adaptation to camera-captured images by distilling the cross-domain knowledge. Experiments on both synthetic and real-world scenarios including comparisons with state-of-the-art methods demonstrate the effectiveness and flexibility of our approach.

中文翻译：

---

具有特征注意力的同时深度立体匹配和去雾

揭示雾层下的密集对应仍然是一项具有挑战性的任务，因为散射效应导致图像特征不太明显。相反，去雾常常被无法在每个像素独立解决的空气光反照率模糊性混淆。在本文中，我们介绍了一种深度卷积神经网络，该网络可以从模糊的立体图像对中同时估计视差和清晰图像。这两项任务都是通过融合来自匹配成本和雾霾传输的深度信息而协同制定的。为了学习深度相关特征的最佳融合，我们提出了一种新颖的编码器-解码器架构，将注意力机制的核心思想扩展到同步立体匹配和去雾。因此，我们的方法估计了散射介质中立体图像的高质量视差，并生成具有增强可见性的外观图像。最后，我们进一步提出了一种通过提取跨域知识来适应相机捕获图像的有效策略。对合成和真实场景的实验，包括与最先进方法的比较，证明了我们方法的有效性和灵活性。