Intrinsic colorization

Liu, Xiaopei; Wan, Liang; Qu, Yingge; Wong, Tien‐Tsin; Lin, Stephen; Leung, Chi-Sing; Heng, Pheng‐Ann

doi:10.1145/1409060.1409105

Cited by 165 publications

(98 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, user registered images captured under different illumination conditions can be used [24,16]. Such an approach can be extended to non-registered web image collections for applications such as colorizing grayscale images [15].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Intrinsic images decomposition using a local and global sparse representation of reflectance

2011

View full text Add to dashboard Cite

Intrinsic image decomposition is an important problem that targets the recovery of shading and reflectance components from a single image. While this is an ill-posed problem on its own, we propose a novel approach for intrinsic image decomposition using a reflectance sparsity prior that we have developed. Our method is based on a simple observation: neighboring pixels usually have the same reflectance if their chromaticities are the same or very similar. We formalize this sparsity constraint on local reflectance, and derive a sparse representation of reflectance components using data-driven edge-avoiding-wavelets. We show that the reflectance component of natural images is sparse in this representation. We also propose and formulate a novel global reflectance sparsity constraint. Using this sparsity prior and global constraints, we formulate a l 1 -regularized least squares minimization problem for intrinsic image decomposition that can be solved efficiently. Our algorithm can successfully extract intrinsic images from a single image, without using other reflection or color models or any user interaction. The results on challenging scenes demonstrate the power of the proposed technique.

show abstract

Section: Related Workmentioning

confidence: 99%

“…σ 2 i is the chromaticity variance in a local window of 5 × 5. Similar formulations to (2) have been used in image segmentation [19,7] and colorization algorithms [14,15]. However, in a twist from previous methods, while we use this formulation to enforce the local sparsity of reflectance, w ij is computed using chromaticity.…”

Section: Reflectance Constraintsmentioning

confidence: 99%

Intrinsic images decomposition using a local and global sparse representation of reflectance

2011

View full text Add to dashboard Cite

show abstract

“…From the comparison of (10) -(12) with our method's equations (3), (4) and (7), we can see two major differences, discussed in the following. Firstly, our diffusion uses the reciprocal function in (4) instead of the exponential one in (11) to measure the smoothness of grey levels. The negative-power exponential function in (11) is actually the reciprocal of the exponential function of grey-level difference.…”

Section: Adding/deleting Strokesmentioning

confidence: 99%

“…Firstly, our diffusion uses the reciprocal function in (4) instead of the exponential one in (11) to measure the smoothness of grey levels. The negative-power exponential function in (11) is actually the reciprocal of the exponential function of grey-level difference. The measurement of (11) can be viewed as the exponential transformation exp( . )…”

Section: Adding/deleting Strokesmentioning

confidence: 99%

Blending-weight diffusion for image colourisation

Chung

2012

IET Image Processing

View full text Add to dashboard Cite

An image colourisation method based on diffusion of colour-blending weights is presented. The authors propose to use reciprocal function for smoothness measurement to determine the priority order of colour propagation in image colourisation. The reciprocal measurement can improve the recent exponential-measurement-based propagation, which has a trend towards being greedy for smooth pixels, and is likely to cause wrong boundaries nearby the object juncture joining the grey levels without significant difference. In addition, the proposed method uses the blending-weight diffusion instead of the direct propagation of chrominance values. By doing so, it can respond quickly to the user demand for stroke editing. Experimental results show that compared with the exponential-measurement-based propagation, the proposed method filled colours more precisely in the positions representing real object surfaces, and saved 85.92% of computation time for adding a stroke and 98.60% for deleting a stroke, to an illustrative image. Compared with two conventional techniques which also implement-blending weights, this method can provide the blending weights for acceptable colourisation by using the economical strokes which positions are less constrained and which sizes are reduced.

show abstract

“…Irony et al [3] proposed an examplebased colorization that performs color transfer over segmented image regions and voting for guaranteeing the spatial consistency. Liu et al [4] also proposed an example-based color transfer in illumination independent domain. The method automatically produces the color scribbles and performs color propagations.…”

Section: Introductionmentioning

confidence: 99%

Part Based Regression with Dimensionality Reduction for Colorizing Monochrome Face Images

Mori

Wada

2013

2013 2nd IAPR Asian Conference on Pattern Recognition

View full text Add to dashboard Cite

This paper presents a method for estimating color face images from near-infrared monochrome face images. This estimation is done by the regression from a monochrome image to a color image. One difficult problem is that the regression depends on face organs. That is, the same intensity pixels in an infrared monochrome image do not correspond to the same color pixels. Therefore, entirely uniform regression cannot colorize the pixels correctly. This paper presents a colorization method for monochrome face images by position-dependent regressions, where the regression coefficients are obtained in different image regions corresponding to facial organs. Also, we can extend the independent variables by adding texture information around the pixels so as to obtain accurate color images. However, unrestricted extension may cause multi-collinearity problem, which may produce inaccurate results. This paper also proposes CCA based dimensionality reduction for avoiding this problem. Comparative experiments on the restoration accuracy demonstrate the superiority of our method.

show abstract

Intrinsic colorization

Cited by 165 publications

References 14 publications

Intrinsic images decomposition using a local and global sparse representation of reflectance

Intrinsic images decomposition using a local and global sparse representation of reflectance

Blending-weight diffusion for image colourisation

Part Based Regression with Dimensionality Reduction for Colorizing Monochrome Face Images

Contact Info

Product

Resources

About