Guided Image Filtering

TLDR

The paper proposes the guided filter, a novel explicit image filter. The guided filter is based on a local linear model that uses a guidance image and can be computed in linear time regardless of kernel size. Experiments demonstrate that the guided filter is an efficient, edge‑preserving smoothing operator that outperforms the bilateral filter near edges and enables diverse applications such as dehazing, feathering, HDR compression, and joint upsampling.

Abstract

In this paper, we propose a novel explicit image filter called guided filter. Derived from a local linear model, the guided filter computes the filtering output by considering the content of a guidance image, which can be the input image itself or another different image. The guided filter can be used as an edge-preserving smoothing operator like the popular bilateral filter [1], but it has better behaviors near edges. The guided filter is also a more generic concept beyond smoothing: It can transfer the structures of the guidance image to the filtering output, enabling new filtering applications like dehazing and guided feathering. Moreover, the guided filter naturally has a fast and nonapproximate linear time algorithm, regardless of the kernel size and the intensity range. Currently, it is one of the fastest edge-preserving filters. Experiments show that the guided filter is both effective and efficient in a great variety of computer vision and computer graphics applications, including edge-aware smoothing, detail enhancement, HDR compression, image matting/feathering, dehazing, joint upsampling, etc.