Inertial Alternating Generalized Forward–Backward Splitting for Image Colorization

Tan, Pauline; Pierre, Fabien; Nikolova, Mila

doi:10.1007/s10851-019-00877-0

Cited by 8 publications

(8 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Let us note that this recent reference shows that the convergence of such numerical schemes can be demonstrated after smoothing of the total variation term. Among all the numerical schemes proposed in the references [60,77], we choose the methodology having the best convergence rate as well as a convergence proof. This scheme is given in Algorithm 2 in [77].…”

Section: A Variational Model For Image Colorization With Channels Couplingmentioning

confidence: 99%

Recent Approaches for Image Colorization

Pierre

Aujol

2021

Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging

Self Cite

View full text Add to dashboard Cite

In the last years, image and video colorization has been considered from many points of view. The technique consists in the addition of a color component to a gray-scale image. This operation needs additional priors which can be given by manual intervention of the user from an example image or be extracted from a large dataset of color images. A very large variety of approaches has been used to solve this problem, like PDE models, non-local methods, variational frameworks, learning approaches, etc. In this chapter, we aim at providing a general overview of state-of-the-art approaches with a focus on few representative methods. Moreover, some recent techniques from the different types of priors (manual, exemplar-based, dataset-based) are explained and compared. The organization of the chapter aims at describing the evolution of the techniques in relation to each other. A focus on some efficient strategies is proposed for each kind of methodology.

show abstract

Section: A Variational Model For Image Colorization With Channels Couplingmentioning

confidence: 99%

Recent Approaches for Image Colorization

Pierre

Aujol

2021

Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…Let us note that this recent reference shows that the convergence of such numerical schemes can be demonstrated after smoothing of the total variation term. Among all the numerical schemes proposed in the references [17,22], we choose the methodology having the best convergence rate as well as a convergence proof. This scheme is given in Algorithm 2 in [22].…”

Section: A Variational Model For Image Colorization With Channels Coumentioning

confidence: 99%

“…Among all the numerical schemes proposed in the references [17,22], we choose the methodology having the best convergence rate as well as a convergence proof. This scheme is given in Algorithm 2 in [22]. This algorithm is a block coordinate forward backward algorithm.…”

Section: A Variational Model For Image Colorization With Channels Coumentioning

confidence: 99%

“…This algorithm is a block coordinate forward backward algorithm. To increase the speed-up of the convergence, Algorithm 2 of [22] is initialized with the result of 500 iterations of the primal-dual algorithm of [17]. Whereas this algorithm has no guaranty of convergence, the authors of [22] have experimentally observed that it numerically converges faster.…”

Section: A Variational Model For Image Colorization With Channels Coumentioning

confidence: 99%

“…In [16], the authors provide a computation time almost equal to 1 sec with unoptimized GPU implementation. Since the minimization scheme of [22] is about the same, the computational time would be almost equal. Thus, the computational time of our approach is not a burden in comparison with the method of [23].…”

Section: Target (Input)mentioning

confidence: 99%

See 2 more Smart Citations

Joint CNN and Variational Model for Fully-Automatic Image Colorization

Mouzon

Pierre

Berger

2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

This paper aims to couple the powerful prediction of the convolutional neural network (CNN) to the accuracy at pixel scale of the variational methods. In this work, the limitations of the CNN-based image colorization approaches are described. We then focus on a CNN which is able to compute a statistical distribution of the colors for each pixel of the image based on a learning stage on a large color image database. After describing its limitation, the variational method of [17] is briefly recalled. This method is able to select a color candidate among a given set while performing regularization of the result. By combining this approach with a CNN, we designed a fully automatic image colorization framework with an improved accuracy in comparison with CNN alone. Some numerical experiments demonstrate the increased accuracy reached by our method.

show abstract