Hardware-Efficient Guided Image Filtering For Multi-Label Problem
Longquan Dai, Mengke Yuan, Zechao Li, Xiaopeng Zhang, Jinhui Tang

TL;DR
This paper introduces a hardware-efficient guided filter (HGF) that significantly improves multichannel image filtering speed and accuracy for multi-label problems by utilizing a novel matrix inverse algorithm and polynomial guidance.
Contribution
The paper proposes a new hardware-efficient guided filter that replaces traditional matrix inversion with element-wise and box filtering operations, enabling faster multichannel filtering.
Findings
HGF achieves state-of-the-art speed in multichannel filtering.
HGF improves accuracy in multi-label image processing.
The polynomial guidance enhances sensitivity to image structure.
Abstract
The Guided Filter (GF) is well-known for its linear complexity. However, when filtering an image with an n-channel guidance, GF needs to invert an n x n matrix for each pixel. To the best of our knowledge existing matrix inverse algorithms are inefficient on current hardwares. This shortcoming limits applications of multichannel guidance in computation intensive system such as multi-label system. We need a new GF-like filter that can perform fast multichannel image guided filtering. Since the optimal linear complexity of GF cannot be minimized further, the only way thus is to bring all potentialities of current parallel computing hardwares into full play. In this paper we propose a hardware-efficient Guided Filter (HGF), which solves the efficiency problem of multichannel guided image filtering and yields competent results when applying it to multi-label problems with synthesized…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Image and Signal Denoising Methods · Advanced Image Fusion Techniques
