论文标题
单个UHD图像通过可解释的金字塔网络除去
Single UHD Image Dehazing via Interpretable Pyramid Network
论文作者
论文摘要
当前，大多数单个图像飞行模型无法实时使用单个GPU着色器来运行超高分辨率（UHD）图像。为了解决这个问题，我们介绍了泰勒定理的无限近似原理，该原理具有拉普拉斯金字塔模式，以构建能够实时处理4K朦胧图像的模型。金字塔网络的n个分支网络对应于泰勒定理中的n个约束项。低阶多项式重建图像的低频信息（例如颜色，照明）。高阶多项式会回归图像的高频信息（例如纹理）。此外，我们提出了一个基于塔克重建的正则化项，该项作用于金字塔模型的每个分支网络。它进一步限制了特征空间中异常信号的产生。广泛的实验结果表明，我们的方法不仅可以在单个GPU（80fps）上实时运行4K图像，而且具有无与伦比的可解释性。 开发的方法在两个基准（O/I-Haze）上实现了最新的（SOTA）性能，并且我们更新的4KID数据集为后续优化方案提供了可靠的基础。
Currently, most single image dehazing models cannot run an ultra-high-resolution (UHD) image with a single GPU shader in real-time. To address the problem, we introduce the principle of infinite approximation of Taylor's theorem with the Laplace pyramid pattern to build a model which is capable of handling 4K hazy images in real-time. The N branch networks of the pyramid network correspond to the N constraint terms in Taylor's theorem. Low-order polynomials reconstruct the low-frequency information of the image (e.g. color, illumination). High-order polynomials regress the high-frequency information of the image (e.g. texture). In addition, we propose a Tucker reconstruction-based regularization term that acts on each branch network of the pyramid model. It further constrains the generation of anomalous signals in the feature space. Extensive experimental results demonstrate that our approach can not only run 4K images with haze in real-time on a single GPU (80FPS) but also has unparalleled interpretability. The developed method achieves state-of-the-art (SOTA) performance on two benchmarks (O/I-HAZE) and our updated 4KID dataset while providing the reliable groundwork for subsequent optimization schemes.
