论文标题
有效的不配对的图像通过环状感知深度监督
Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision
论文作者
论文摘要
没有配对的无雾图图像的图像除尘非常重要，因为获得配对的图像通常需要大量成本。但是，我们观察到，以前未配对的图像去悬空方法往往会遭受深度边界附近的性能降解，而深度往往会突然变化。因此，我们建议通过循环感知深度监督在未配对的图像中退化深度边界退化。再加上发电机和鉴别器的双路径功能，我们的模型可实现$ \ Mathbf {20.36} $在NYU DEPTH V2数据集上的信噪比（PSNR），从而极大地超过了其预先的浮动点操作（FLOPP）。
Image dehazing without paired haze-free images is of immense importance, as acquiring paired images often entails significant cost. However, we observe that previous unpaired image dehazing approaches tend to suffer from performance degradation near depth borders, where depth tends to vary abruptly. Hence, we propose to anneal the depth border degradation in unpaired image dehazing with cyclic perceptual-depth supervision. Coupled with the dual-path feature re-using backbones of the generators and discriminators, our model achieves $\mathbf{20.36}$ Peak Signal-to-Noise Ratio (PSNR) on NYU Depth V2 dataset, significantly outperforming its predecessors with reduced Floating Point Operations (FLOPs).
