Local Laplacian Filters: Edge-aware Image Processing with a Laplacian Pyramid
Local Laplacian Filters: Edge-aware Image Processing with a Laplacian Pyramid
复制标题
DOI：
10.1145/1964921.1964963
复制
发表时间：
2011-07-01
影响因子：
6.2
通讯作者：
Kautz, Jan
中科院分区：
文献类型：
--
作者：
Paris, Sylvain;Hasinoff, Samuel W.;Kautz, Jan
Laplacian金字塔无处不在，可将图像分解为多个尺度，并广泛用于图像分析。但是，由于它是由空间不变的高斯内核构造的，因此被认为是无法很好地表示边缘的Laplacian金字塔，并且不适合用于边缘感知的操作，例如Edge-Edge-Edge-Presserveling Placherving ploothering ploolying sploothing和tone映射。为了解决这些任务，已经提出了许多替代技术和表示形式。 g。，各向异性扩散，邻居滤波和专门的小波底座。尽管这些方法已显示出成功的结果，但它们以额外的复杂性为代价，通常伴随着更高的计算成本或需要后处理产生的结果。在本文中，我们使用标准的拉普拉斯金字塔展示了最先进的边缘感知处理。我们对像素值的简单阈值表征边缘，使我们能够将大规模边缘与小规模的细节区分开。在此结果的基础上，我们提出了一组图像过滤器，以实现边缘提供平滑，细节增强，音调映射和反向音调映射。我们方法的优点是它的简单性和灵活性，仅依靠简单的非线性和小高斯卷积。无需优化或后处理。正如我们所证明的那样，我们的方法会产生一贯的高质量结果，而不会降解边缘或引入光晕。
The Laplacian pyramid is ubiquitous for decomposing images into multiple scales and is widely used for image analysis. However, because it is constructed with spatially invariant Gaussian kernels, the Laplacian pyramid is widely believed as being unable to represent edges well and as being ill-suited for edge-aware operations such as edge-preserving smoothing and tone mapping. To tackle these tasks, a wealth of alternative techniques and representations have been proposed, e. g., anisotropic diffusion, neighborhood filtering, and specialized wavelet bases. While these methods have demonstrated successful results, they come at the price of additional complexity, often accompanied by higher computational cost or the need to post-process the generated results. In this paper, we show state-of-the-art edge-aware processing using standard Laplacian pyramids. We characterize edges with a simple threshold on pixel values that allows us to differentiate large-scale edges from small-scale details. Building upon this result, we propose a set of image filters to achieve edge-preserving smoothing, detail enhancement, tone mapping, and inverse tone mapping. The advantage of our approach is its simplicity and flexibility, relying only on simple point-wise nonlinearities and small Gaussian convolutions; no optimization or post-processing is required. As we demonstrate, our method produces consistently high-quality results, without degrading edges or introducing halos.