Side Window Filtering

Abstract

Local windows are routinely used in computer vision and almost without exception the center of the window is aligned with the pixels being processed. We show that this conventional wisdom is not universally applicable. When a pixel is on an edge, placing the center of the window on the pixel is one of the fundamental reasons that cause many filtering algorithms to blur the edges. Based on this insight, we propose a new Side Window Filtering (SWF) technique which aligns the window's side or corner with the pixel being processed. The SWF technique is surprisingly simple yet theoretically rooted and very effective in practice. We show that many traditional linear and nonlinear filters can be easily implemented under the SWF framework. Extensive analysis and experiments show that implementing the SWF principle can significantly improve their edge preserving capabilities and achieve state of the art performances in applications such as image smoothing, denoising, enhancement, structure-preserving texture-removing, mutual-structure extraction, and HDR tone mapping. In addition to image filtering, we further show that the SWF principle can be extended to other applications involving the use of a local window. Using colorization by optimization as an example, we demonstrate that implementing the SWF principle can effectively prevent artifacts such as color leakage associated with the conventional implementation. Given the ubiquity of window based operations in computer vision, the new SWF technique is likely to benefit many more applications.

Fabric Defect Detection Based on Illumination Correction and Visual Salient Features

“…The traditional method of extracting image illumination component by multi-scale rolling guidance filter [ 24 ] has some defects, for example, damaged image edge and illumination components appear halo phenomenon. The side window filter (SWF) [ 33 ] can preserve the edge of the image very well, so we use multi-scale side window box filter to extract the illumination components of fabric images. Considering that HSV color space is more consistent with the visual characteristics of human eyes, and the hue (H), saturation (S), and value (V) in HSV color space are independent of each other, the operation of V will not affect the color information of the image.…”

“…In order to simplify the process, we adopt the proposal of the paper [ 33 ], and define eight side windows only in the discrete cases, as shown in Figure 2 b–d. These eight windows defined here correspond to , .…”

EMCM: A Novel Binary Edge-Feature-Based Maximum Clique Framework for Multispectral Image Matching

“…The workflow of the whole algorithm is exhibited in Figure 2a. First, we obtained the edge map pair of the given multispectral image pair via a state-of-the-art box filter, termed as the sub-window box filter [36], and our previously proposed strong edge-detection algorithm, named GWW [37], as shown in Figure 2d,e. Then, we detected keypoints on strong edges of the edge map pair and encoded their local edges with binary edge feature descriptors, named Edge Binary Shape Context (abbreviated as EBSC), as shown in Figure 2f,g.…”

“…In order to overcome the limitation of the GWW, we present a method, S-GWW, to extract a strong edge map. A box filter, as an edge-preserving filter, can be used for effectively preserving corner and edge information while smoothing the image, and the edge-preserving effect of the box filter is better than the guided filter [36]. A box filter transforms the traditional non-edge-preserving box filter into a margin-preserving filter without increasing computational complexity, while it removes the noise to improve the edge features (see Figure 5c label 1 and label 2).…”

A General Perceptual Infrared and Visible Image Fusion Framework Based on Linear Filter and Side Window Filtering Technology

“…In CVPR 2019, Yin and Gong et al proposed a side window filtering (SWF) framework [20]. Most linear filters and nonlinear filters can significantly improve their edgepreserving capabilities by using this framework.…”