.png){kind=icon}
Return
Structure-aware filter using self-guided information
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jvcir.2025.104677.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Structure-aware smoothing has proven to be a fundamental tool for a wide range of applications in computer vision and image processing tasks. In this paper, we propose an efficient and effective filter to smooth out texture. The proposed filter is implemented in three steps. (1) An image with a weak textured component is generated by applying a linear filter on the original image. (2) A windowed inherent variation is employed to discriminate textures and structures, and is used as a structure indicator. (3) Pixels on the flat and structure areas, guided by the structure indicator, are locally selected from the input and blurred image (from step (1)) through a local interpolation process. We have also presented detailed experimental analysis of the proposed technique including how the filter is related to self-guided filter and anisotropic filter. We demonstrate that the proposed technique outperforms several state-of-the-art methods in subjective and objective evaluation.
Journal
IF:
3.1
Papers:
532
Citations:
5.6K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
View more