Image filtering is an important and fundamental issue in image processing pipelines and find itself a lot of applications in segmentation, salient features detection, colorization, stylization and so on. In recent years, several nonlinear filters aiming at edge-preserving smoothing has been proposed from different fields. However, none of these filters is perfect for all applications due to their own model assumption and solving strategy. In this paper, we give a brief introduction to several of them particularly from graphics field and comparison about their advantages and limitations through experiments. We look forward to offer an helpful starting point for researchers to select or improve them.
Image gradients which present directional changes of pixel values in an image are widely considered as important
clues for salient features like edges. However, it is difficult to distinguish edges from details which also have large
gradients merely based on gradients. In this paper, we propose a novel model called relative gradient which can
overcome the problem and better distinguish edges from flat regions and details. We demonstrate the effectiveness of our
model by improving some representative algorithms using the relative gradient instead of traditional gradient in contexts
of edge detection and non-linear filtering. More applications can be found in image processing, analysis and related
Edge-preserving smoothing is crucial for image decomposition to extract the base layer. However, current methods
fail to smooth high-contrast details or preserve thin edges due to their single criterion for distinguishing edges and details.
In this paper, we present a hybrid definition for salient edges using two properties: intensity amplitude and oscillations
density. Based on this definition, we propose an edge-preserving image smoothing algorithm. Firstly local extrema of the
input image are located. Then these extrema points are classified into edge or detail points by the two properties. Thirdly,
max and min envelops are obtained by an optimizing process with edge points as constrains. Lastly, the smoothing result
is obtained by an averaging operation. Experimental results show that the proposed method can preserve salient step
edges while smoothing high-contrast details and is useful in many applications such as image enhancement and