Real-time Image Smoothing via Iterative Least Squares

Liu, Wei; Zhang, Pingping; Huang, Xiaolin; Yang, Jie; Shen, Chunhua; Reid, Ian

doi:10.1145/3388887

Cited by 81 publications

(53 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results obtained are shown in Fig. 5 for the image filters: WMF [26], RTV [24], RGF [25], ILS [11], WLS [5] and L 0 [23], and in Fig. 6 for the bilateral filter (BF), LLF [14] and LE [18].…”

Section: Numerical Experiments and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Two iterative methods for reverse image filtering

Belyaev

Fayolle

2021

SIViP

View full text Add to dashboard Cite

We consider the problem of recovering an original image $${\varvec{x}}$$ x from its filtered version $${\varvec{y}}={\varvec{f}}({\varvec{x}})$$ y = f ( x ) , assuming that the internal structure of the filter $${\varvec{f}}(\cdot )$$ f ( · ) is unknown to us (i.e., we can only query the filter as a black-box and, for example, cannot invert it). We present two new iterative methods to attack the problem, analyze, and evaluate them on various smoothing and edge-preserving image filters.

show abstract

Section: Numerical Experiments and Discussionmentioning

confidence: 99%

“…Bottom row: the corresponding defiltered images. For each filtered image, for each channel, the number of reverse filtering iterations is determined by(11) with t = 0.0005. a Wiener filtering and defilering with (3). bPillbox filtering and defiltering with (3).…”

mentioning

confidence: 99%

Two iterative methods for reverse image filtering

Belyaev

Fayolle

2021

SIViP

View full text Add to dashboard Cite

show abstract

“…The WLS smoothing is a strong baseline in the literature that performs well in handling gradient reversals and halos. However, it can also produce intensity shift in the results [3], [50]. On the one hand, the intensity shift can be adopted to enhance the image contrast, which is appealing in image detail enhancement, as shown in the first row of Fig.…”

Section: Tasks In the First Groupmentioning

confidence: 99%

“…7 (b) and (d). On the other hand, the intensity shift can lead to compartmentalization artifacts in some cases [21], [50]. One example of image detail enhancement is illustrated in the second row of Fig.…”

Section: Tasks In the First Groupmentioning

confidence: 99%

A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing

Liu¹,

Zhang²,

Lei³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Image smoothing is a fundamental procedure in applications of both computer vision and graphics. The required smoothing properties can be different or even contradictive among different tasks. Nevertheless, the inherent smoothing nature of one smoothing operator is usually fixed and thus cannot meet the various requirements of different applications. In this paper, we first introduce the truncated Huber penalty function which shows strong flexibility under different parameter settings. A generalized framework is then proposed with the introduced truncated Huber penalty function. When combined with its strong flexibility, our framework is able to achieve diverse smoothing natures where contradictive smoothing behaviors can even be achieved. It can also yield the smoothing behavior that can seldom be achieved by previous methods, and superior performance is thus achieved in challenging cases. These together enable our framework capable of a range of applications and able to outperform the state-of-the-art approaches in several tasks, such as image detail enhancement, clip-art compression artifacts removal, guided depth map restoration, image texture removal, etc. In addition, an efficient numerical solution is provided and its convergence is theoretically guaranteed even the optimization framework is non-convex and non-smooth. A simple yet effective approach is further proposed to reduce the computational cost of our method while maintaining its performance. The effectiveness and superior performance of our approach are validated through comprehensive experiments in a range of applications. Our code is available at https://github.com/wliusjtu/Generalized-Smoothing-Framework.

show abstract

“…Image smoothing filters are used to minimize colour differences in the image and highlight sparse structures [12]. Smoothing is an essential process for many computer vision applications [13]. In algorithms with image smoothing, gradient size is generally used as a hint [14].…”

Section: Introductionmentioning

confidence: 99%

A New Hybrid Filter Approach for Image Processing

Aksoy

Salman

2020

Sakarya University Journal of Computer and Information Sciences

View full text Add to dashboard Cite

Today, with the rapidly advancing technology, the importance of image processing techniques is increasing. Image processing is used in many areas from facial recognition to plant disease identification. One of the important image processing stages is the filtering stage used for smoothing images and object detection. Among these filtering techniques, basic filtering techniques such as mean, median and Gaussian are used in image processing. However, these filtering techniques are known to be insufficient to achieve the desired results in some cases. In this study, a new hybrid filtering approach named Mean-Median-Gaussian (MMG) is presented using these three basic filtering techniques. It has been demonstrated that the obtained MMG hybrid algorithm gives more successful results than these three basic filtering techniques in smoothing the images and determining the boundary lines.

show abstract

Real-time Image Smoothing via Iterative Least Squares

Cited by 81 publications

References 53 publications

Two iterative methods for reverse image filtering

Two iterative methods for reverse image filtering

A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing

A New Hybrid Filter Approach for Image Processing

Contact Info

Product

Resources

About