Fast Bilateral Filteringfor the Display of High-Dynamic-Range Images

本文主要是介绍Fast Bilateral Filteringfor the Display of High-Dynamic-Range Images，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

1 Title

Fast Bilateral Filtering for the Display of High-Dynamic-Range Images(Fr´edo Durand and Julie Dorsey)【SIGGRAPH '02】

2 Conclusion

This paper presents a new technique for the display of high-dynamic-range images, which reduces the contrast while preserving detail. It is based on a two-scale decomposition of the image into a base layer, encoding large-scale variations, and a detail layer. Only the base
layer has its contrast reduced, thereby preserving detail. The base layer is obtained using an edge-preserving filter called the bilateral filter. This is a non-linear filter, where the weight of each pixel is computed using a Gaussian in the spatial domain multiplied by an influence function in the intensity domain that decreases the weight of pixels with large intensity differences.

3 Good Sentences

1、Our work is motivated by the idea that the use of high-dynamicrange cameras and relevant display operators can address these issues. Digital photography has inherited many of the strengths of film photography. However it also has the potential to overcome its limitations.(reason: This is the motivation which has activate this study)
2、The primary focus of this paper is the development of a fast and robust edge-preserving filter – that is, a filter that blurs the small variations of a signal (noise or texture detail) but preserves the large discontinuities (edges). Our application is unusual however, in that the noise (detail) is the important information in the signal and must therefore be preserved(reason: This is the contribution of this study which make it greatful)
3、. Moreover, the coefficients of their diffusion equation must be adapted to each image, which makes this method more difficult to use, and the extension to animated sequences unclear. We build upon a different edge-preserving filter that is easier to control and more amenable to acceleration.(reason: This is the problems of previous works and the solutions that this study has found out)

高动态范围图像（High-Dynamic Range，简称HDR），相比普通的图像，可以提供更多的动态范围和图像细节，根据不同的曝光时间的LDR(Low-Dynamic Range)图像，利用每个曝光时间相对应最佳细节的LDR图像来合成最终HDR图像，能够更好的反映人真实环境中的视觉效果。但是想要HDR图像在显示器中显示，需要对其数据进行处理，如何处理即能充分利用这些数据，又能使得图像的显示尽量不丢失细节，是多年来不少图像工作者研究的重点。
最简单的方法是线性隐射，先算出离散数据的最大值和最小值，然后将数据线性的拉升至0到255之间，这种直接的操作往往无法得到满意的效果，会导致大量细节丢失，表现在视觉上就是一大块黑色或者一大块白色的。很多人针对这一问题做出了研究和改进。而这篇论文提出方法：基于快速双边滤波技术的HDR显示过程。其目标是压缩高动态范围图像，使其能够用于显示。它可以在保留细节的同时降低对比度。
它的基本原理是将图像分为两个尺度：即base layer和detail layer，降低前者的对比度，后者不变；2.base layer 用双边滤波器进行处理，一般双边滤波是用于去掉方差小的噪声，保边。但是本文的方法中，噪声，也就是细节，是一种重要的信息，因此需要保存下来。
算法的简单流程如下所示：