Enhanced Edge-Perceptual Guided Image Filtering

TL;DR

This paper introduces a new guided image filter that enhances edge preservation and reduces artifacts by integrating explicit edge-protect and residual constraints, improving performance in various image processing tasks.

Contribution

The paper proposes a novel guided image filter with explicit constraints that significantly improves edge preservation and reduces halo artifacts compared to existing methods.

Findings

Improved edge-preserving ability demonstrated in experiments

Effective in detail enhancement and exposure fusion

Reduces halo artifacts in guided filtering

Abstract

Due to the powerful edge-preserving ability and low computational complexity, Guided image filter (GIF) and its improved versions has been widely applied in computer vision and image processing. However, all of them are suffered halo artifacts to some degree, as the regularization parameter increase. In the case of inconsistent structure of guidance image and input image, edge-preserving ability degradation will also happen. In this paper, a novel guided image filter is proposed by integrating an explicit first-order edge-protect constraint and an explicit residual constraint which will improve the edge-preserving ability in both cases. To illustrate the efficiency of the proposed filter, the performances are shown in some typical applications, which are single image detail enhancement, multi-scale exposure fusion, hyper spectral images classification. Both theoretical analysis and experimental results prove that the powerful edge-preserving ability of the proposed filter.