Abstract
Single image dehazing is a critical image pre-processing step for subsequent high-level computer vision tasks. However, it remains challenging due to its ill-posed nature. Existing dehazing models tend to suffer from model overcomplexity and computational inefficiency or have limited representation capacity. To tackle these challenges, here we propose a fast and accurate multi-scale end-to-end dehazing network called FAMED-Net, which comprises encoders at three scales and a fusion module to efficiently and directly learn the haze-free image. Each encoder consists of cascaded and densely connected point-wise convolutional layers and pooling layers. Since no larger convolutional kernels are used and features are reused layer-by-layer, FAMED-Net is lightweight and computationally efficient. Thorough empirical studies on public synthetic datasets (including RESIDE) and real-world hazy images demonstrate the superiority of FAMED-Net over other representative state-of-the-art models with respect to model complexity, computational efficiency, restoration accuracy, and cross-set generalization. The code will be made publicly available.
Abstract (translated)
单图像去杂是后续高层次计算机视觉任务的关键图像预处理步骤。然而，由于其不适定的性质，它仍然具有挑战性。现有的去津模型往往存在模型过于复杂、计算效率低下或表示能力有限等问题。为了应对这些挑战，本文提出了一种快速、准确的多尺度端到端去杂网，称为Famed网，它包括三个尺度的编码器和一个融合模块，以有效、直接地学习无雾图像。每个编码器由级联和密集连接的点向卷积层和汇集层组成。由于不需要使用较大的卷积核，而且特性可以逐层重复使用，因此Famed网络重量轻，计算效率高。通过对公共合成数据集（包括驻留）和真实模糊图像的深入实证研究，证明了在模型复杂度、计算效率、恢复精度和交叉集泛化等方面，著名网络优于其他具有代表性的最新模型。代码将公开发布。
URL
https://arxiv.org/abs/1906.04334
