Enhanced Edge-Perceptual Guided Image Filtering
- URL: http://arxiv.org/abs/2310.10387v1
- Date: Mon, 16 Oct 2023 13:27:46 GMT
- Title: Enhanced Edge-Perceptual Guided Image Filtering
- Authors: Jinyu Li
- Abstract summary: A novel guided image filter is proposed by integrating an explicit first-order edge-protect constraint and an explicit residual constraint.
The performances are shown in some typical applications, which are single image detail enhancement, multi-scale exposure fusion, hyper spectral images classification.
- Score: 27.61180330004451
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Improved Anisotropic Gaussian Filters [1.2499537119440245]
Elongated anisotropic Gaussian filters are used for the orientation estimation of fibers.
This paper proposes a modified algorithm for 2D anisotropic Gaussian filters and shows that this improves their precision.
arXiv Detail & Related papers (2023-03-23T13:59:57Z) - Parallax-Tolerant Unsupervised Deep Image Stitching [57.76737888499145]
We propose UDIS++, a parallax-tolerant unsupervised deep image stitching technique.
First, we propose a robust and flexible warp to model the image registration from global homography to local thin-plate spline motion.
To further eliminate the parallax artifacts, we propose to composite the stitched image seamlessly by unsupervised learning for seam-driven composition masks.
arXiv Detail & Related papers (2023-02-16T10:40:55Z) - Panchromatic and Multispectral Image Fusion via Alternating Reverse
Filtering Network [23.74842833472348]
Pan-sharpening refers to super-resolve the low-resolution (LR) multi-spectral (MS) images in the spatial domain.
We present a simple yet effective textitalternating reverse filtering network for pan-sharpening.
arXiv Detail & Related papers (2022-10-15T03:56:05Z) - On Measuring and Controlling the Spectral Bias of the Deep Image Prior [63.88575598930554]
The deep image prior has demonstrated the remarkable ability that untrained networks can address inverse imaging problems.
It requires an oracle to determine when to stop the optimization as the performance degrades after reaching a peak.
We study the deep image prior from a spectral bias perspective to address these problems.
arXiv Detail & Related papers (2021-07-02T15:10:42Z) - Unsharp Mask Guided Filtering [53.14430987860308]
The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering.
We propose a new and simplified formulation of the guided filter inspired by unsharp masking.
Our formulation enjoys a filtering prior to a low-pass filter and enables explicit structure transfer by estimating a single coefficient.
arXiv Detail & Related papers (2021-06-02T19:15:34Z) - Universal and Flexible Optical Aberration Correction Using Deep-Prior
Based Deconvolution [51.274657266928315]
We propose a PSF aware plug-and-play deep network, which takes the aberrant image and PSF map as input and produces the latent high quality version via incorporating lens-specific deep priors.
Specifically, we pre-train a base model from a set of diverse lenses and then adapt it to a given lens by quickly refining the parameters.
arXiv Detail & Related papers (2021-04-07T12:00:38Z) - Towards Unsupervised Deep Image Enhancement with Generative Adversarial
Network [92.01145655155374]
We present an unsupervised image enhancement generative network (UEGAN)
It learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner.
Results show that the proposed model effectively improves the aesthetic quality of images.
arXiv Detail & Related papers (2020-12-30T03:22:46Z) - Image Inpainting with Learnable Feature Imputation [8.293345261434943]
A regular convolution layer applying a filter in the same way over known and unknown areas causes visual artifacts in the inpainted image.
We propose (layer-wise) feature imputation of the missing input values to a convolution.
We present comparisons on CelebA-HQ and Places2 to current state-of-the-art to validate our model.
arXiv Detail & Related papers (2020-11-02T16:05:32Z) - Adaptive Debanding Filter [55.42929350861115]
Banding artifacts manifest as staircase-like color bands on pictures or video frames.
We propose a content-adaptive smoothing filtering followed by dithered quantization, as a post-processing module.
Experimental results show that our proposed debanding filter outperforms state-of-the-art false contour removing algorithms both visually and quantitatively.
arXiv Detail & Related papers (2020-09-22T20:44:20Z) - Improved Adaptive Type-2 Fuzzy Filter with Exclusively Two Fuzzy
Membership Function for Filtering Salt and Pepper Noise [30.639740354770282]
fuzzy filter is proposed for filtering salt and pepper noise from the images.
The proposed filter is validated on standard images with various noise levels.
The performance of the proposed filter is compared with the various state-of-the-art methods in terms of peak signal-to-noise ratio and computation time.
arXiv Detail & Related papers (2020-08-10T13:18:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.