Directional Bilateral Filters
Manasij Venkatesh, Chandra Sekhar Seelamantula

TL;DR
This paper introduces a directional bilateral filter that incorporates local orientation information via an oriented Gaussian domain kernel, improving edge-preserving smoothing and denoising performance over traditional bilateral filters.
Contribution
The paper presents a novel directional bilateral filter with a locally controlled domain kernel based on structure tensors, and optimizes parameters using Stein's unbiased risk estimate.
Findings
Outperforms Gaussian bilateral filter in PSNR across noise levels
Effective in suppressing outliers while smoothing
Validated on synthetic and real endoscopic images
Abstract
We propose a bilateral filter with a locally controlled domain kernel for directional edge-preserving smoothing. Traditional bilateral filters use a range kernel, which is responsible for edge preservation, and a fixed domain kernel that performs smoothing. Our intuition is that orientation and anisotropy of image structures should be incorporated into the domain kernel while smoothing. For this purpose, we employ an oriented Gaussian domain kernel locally controlled by a structure tensor. The oriented domain kernel combined with a range kernel forms the directional bilateral filter. The two kernels assist each other in effectively suppressing the influence of the outliers while smoothing. To find the optimal parameters of the directional bilateral filter, we propose the use of Stein's unbiased risk estimate (SURE). We test the capabilities of the kernels separately as well as together,…
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.
