Fast Edge-Aware Processing via First Order Proximal Approximation

Badri, Hicham; Yahia, Hussein; Aboutajdine, Driss

doi:10.1109/tvcg.2015.2396064

Cited by 22 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in Section 4.4 in detail. While Badri et al [29] used a similar nonconvex objective function for image smoothing, our model provides a more generalized objective for joint image filtering. Shen et al [30] used the common structure in input and guidance images, but the local filtering formulation of the filter introduces halo artifacts and limits the applicability.…”

Section: Image Filtering and Joint Image Filteringmentioning

confidence: 99%

See 1 more Smart Citation

Robust Guided Image Filtering Using Nonconvex Potentials

Ham

Cho

Ponce

2018

IEEE Trans. Pattern Anal. Mach. Intell.

185

172

View full text Add to dashboard Cite

Filtering images using a guidance signal, a process called guided or joint image filtering, has been used in various tasks in computer vision and computational photography, particularly for noise reduction and joint upsampling. This uses an additional guidance signal as a structure prior, and transfers the structure of the guidance signal to an input image, restoring noisy or altered image structure. The main drawbacks of such a data-dependent framework are that it does not consider structural differences between guidance and input images, and that it is not robust to outliers. We propose a novel SD (for static/dynamic) filter to address these problems in a unified framework, and jointly leverage structural information from guidance and input images. Guided image filtering is formulated as a nonconvex optimization problem, which is solved by the majorize-minimization algorithm. The proposed algorithm converges quickly while guaranteeing a local minimum. The SD filter effectively controls the underlying image structure at different scales, and can handle a variety of types of data from different sensors. It is robust to outliers and other artifacts such as gradient reversal and global intensity shift, and has good edge-preserving smoothing properties. We demonstrate the flexibility and effectiveness of the proposed SD filter in a variety of applications, including depth upsampling, scale-space filtering, texture removal, flash/non-flash denoising, and RGB/NIR denoising.

show abstract

Section: Image Filtering and Joint Image Filteringmentioning

confidence: 99%

“…4. The SD filter of (11) applies the very popular WLS filter [23] iteratively with a fixed input image, allowing us to use many acceleration techniques for WLS filtering [29], [55]. When using MEX implementation of the fast WLS algorithm in [55], we obtain the filtering result with 0.1 seconds for the same image size.…”

Section: Runtimementioning

confidence: 99%

Robust Guided Image Filtering Using Nonconvex Potentials

Ham

Cho

Ponce

2018

IEEE Trans. Pattern Anal. Mach. Intell.

185

172

View full text Add to dashboard Cite

show abstract

“…All the solvers are implemented in MATLAB. For the PCG solver, we adopt the MATLAB build-in incomplete Cholesky factorization preconditioner which is faster than the one presented in [Krishnan et al 2013] as reported by Badri et al [Badri et al 2013[Badri et al , 2015. For both of the intensity domain solvers, the time of constructing the Laplacian matrix is also included in the measured time.…”

Section: Iterative Least Squaresmentioning

confidence: 99%

Real-time Image Smoothing via Iterative Least Squares

Liu¹,

Zhang²,

Huang³

et al. 2020

Preprint

View full text Add to dashboard Cite

Edge-preserving image smoothing is a fundamental procedure for many computer vision and graphic applications. There is a tradeoff between the smoothing quality and the processing speed: the high smoothing quality usually requires a high computational cost which leads to the low processing speed. In this paper, we propose a new global optimization based method, named iterative least squares (ILS), for efficient edge-preserving image smoothing. Our approach can produce high-quality results but at a much lower computational cost. Comprehensive experiments demonstrate that the propose method can produce results with little visible artifacts. Moreover, the computation of ILS can be highly parallel, which can be easily accelerated through either multi-thread computing or the GPU hardware. With the acceleration of a GTX 1080 GPU, it is able to process images of 1080p resolution (1920 × 1080) at the rate of 20fps for color images and 47fps for gray images. In addition, the ILS is flexible and can be modified to handle more applications that require different smoothing properties. Experimental results of several applications show the effectiveness and efficiency of the proposed method. The code is available at https://github.com/wliusjtu/Realtime-Image-Smoothing-via-Iterative-Least-Squares CCS Concepts: • Computing methodologies → Computational photography; Image processing.

show abstract

“…Unfortunately, this inverse function cannot be evaluated directly for the l p -norm. However, a solution can be approximated via a first-order Taylor expansion [39] :…”

Section: Appendix L P -Shrinkage Solutionmentioning

confidence: 99%

A Non-Local Low-Rank Approach to Enforce Integrability

Badri

Yahia

2016

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

We propose a new approach to enforce integrability using recent advances in non-local methods. Our formulation consists in a sparse gradient data-fitting term to handle outliers together with a gradient-domain non-local low-rank prior. This regularization has two main advantages: 1) the low-rank prior ensures similarity between non-local gradient patches, which helps recovering high-quality clean patches from severe outliers corruption and 2) the low-rank prior efficiently reduces dense noise as it has been shown in recent image restoration works. We propose an efficient solver for the resulting optimization formulation using alternate minimization. Experiments show that the new method leads to an important improvement compared with previous optimization methods and is able to efficiently handle both outliers and dense noise mixed together.

show abstract

Fast Edge-Aware Processing via First Order Proximal Approximation

Cited by 22 publications

References 29 publications

Robust Guided Image Filtering Using Nonconvex Potentials

Robust Guided Image Filtering Using Nonconvex Potentials

Real-time Image Smoothing via Iterative Least Squares

A Non-Local Low-Rank Approach to Enforce Integrability

Contact Info

Product

Resources

About