Blur Invariants for Image Recognition
- URL: http://arxiv.org/abs/2301.07581v1
- Date: Wed, 18 Jan 2023 14:58:32 GMT
- Title: Blur Invariants for Image Recognition
- Authors: Jan Flusser, Matej Lebl, Matteo Pedone, Filip Sroubek, and Jitka
Kostkova
- Abstract summary: Invariants with respect to blur offer an alternative way of adescription and recognition of blurred images without any deblurring.
In this paper, we present an original unified theory of blur invariants.
- Score: 9.207644534257543
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Blur is an image degradation that is difficult to remove. Invariants with
respect to blur offer an alternative way of a~description and recognition of
blurred images without any deblurring. In this paper, we present an original
unified theory of blur invariants. Unlike all previous attempts, the new theory
does not require any prior knowledge of the blur type. The invariants are
constructed in the Fourier domain by means of orthogonal projection operators
and moment expansion is used for efficient and stable computation. It is shown
that all blur invariants published earlier are just particular cases of this
approach. Experimental comparison to concurrent approaches shows the advantages
of the proposed theory.
Related papers
- Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains [19.573629029170128]
This paper presents an innovative framework designed to train an image deblurring algorithm tailored to a specific camera device.
It works by transforming a blurry input image, which is challenging to deblur, into another blurry image that is more amenable to deblurring.
arXiv Detail & Related papers (2024-03-24T15:58:48Z) - Image Moment Invariants to Rotational Motion Blur [47.76259900246576]
This paper proposes a novel method to generate image moment invariants under general rotational motion blur.
To the best of our knowledge, this is the first time that moment invariants for rotational motion blur have been proposed in the literature.
Our results show that the moment invariants proposed in this paper significantly outperform other features in various tasks.
arXiv Detail & Related papers (2023-03-25T21:23:42Z) - Improving Diffusion Models for Inverse Problems using Manifold Constraints [55.91148172752894]
We show that current solvers throw the sample path off the data manifold, and hence the error accumulates.
To address this, we propose an additional correction term inspired by the manifold constraint.
We show that our method is superior to the previous methods both theoretically and empirically.
arXiv Detail & Related papers (2022-06-02T09:06:10Z) - Point spread function estimation for blind image deblurring problems
based on framelet transform [0.0]
The approximation of the image that has been lost due to the blurring process is an important issue in image processing.
The second type of problem is more complex in terms of calculations than the first problems due to the unknown of original image and point spread function estimation.
An algorithm based on coarse-to-fine iterative by $l_0-alpha l_1$ regularization and framelet transform is introduced to approximate the spread function estimation.
The proposed method is investigated on different kinds of images such as text, face, natural.
arXiv Detail & Related papers (2021-12-21T06:15:37Z) - Deblurring via Stochastic Refinement [85.42730934561101]
We present an alternative framework for blind deblurring based on conditional diffusion models.
Our method is competitive in terms of distortion metrics such as PSNR.
arXiv Detail & Related papers (2021-12-05T04:36:09Z) - Low-Light Image Enhancement with Normalizing Flow [92.52290821418778]
In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model.
An invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution.
The experimental results on the existing benchmark datasets show our method achieves better quantitative and qualitative results, obtaining better-exposed illumination, less noise and artifact, and richer colors.
arXiv Detail & Related papers (2021-09-13T12:45:08Z) - Mutual Affine Network for Spatially Variant Kernel Estimation in Blind
Image Super-Resolution [130.32026819172256]
Existing blind image super-resolution (SR) methods mostly assume blur kernels are spatially invariant across the whole image.
This paper proposes a mutual affine network (MANet) for spatially variant kernel estimation.
arXiv Detail & Related papers (2021-08-11T16:11:17Z) - Geometric Moment Invariants to Motion Blur [4.8915390363596005]
We focus on removing interference of motion blur by the derivation of motion blur invariants.
Based on geometric moment and mathematical model of motion blur, we prove that geometric moments of blurred image and original image are linearly related.
Surprisingly, we find some geometric moment invariants are invariants to not only spatial transform but also motion blur.
arXiv Detail & Related papers (2021-01-21T14:50:34Z) - Deep Variational Network Toward Blind Image Restoration [60.45350399661175]
Blind image restoration is a common yet challenging problem in computer vision.
We propose a novel blind image restoration method, aiming to integrate both the advantages of them.
Experiments on two typical blind IR tasks, namely image denoising and super-resolution, demonstrate that the proposed method achieves superior performance over current state-of-the-arts.
arXiv Detail & Related papers (2020-08-25T03:30:53Z) - End-to-end Interpretable Learning of Non-blind Image Deblurring [102.75982704671029]
Non-blind image deblurring is typically formulated as a linear least-squares problem regularized by natural priors on the corresponding sharp picture's gradients.
We propose to precondition the Richardson solver using approximate inverse filters of the (known) blur and natural image prior kernels.
arXiv Detail & Related papers (2020-07-03T15:45:01Z)
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.