Interactive Image Colorization Using Laplacian Coordinates

Casaca, Wallace; Colnago, Marilaine; Nonato, Luís Gustavo

doi:10.1007/978-3-319-23117-4_58

Cited by 12 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…User-guided methods work by propagating manually provided colorization hints (some of the colors and strokes) to the surrounding areas. In the past, color propagation was based on low level similarities such as changes in luminance [18], [24], [25], [30], [31]. Pierre et al proposed a method to combine example color images with colorization hints [18].…”

Section: Related Workmentioning

confidence: 99%

A Practical Monochrome Video Colorization Framework for Broadcast Program Production

Endo

Kawai

Mchizuki

2021

IEEE Trans. on Broadcast.

View full text Add to dashboard Cite

Techniques of using convolutional neural networks (CNNs) to colorize monochrome still images have been widely researched. However, the results of automatic colorization are often different from the user's intentions and historical fact. A lot of color correction work still needs to be done in order to produce a colorized video. This is a major problem in situations such as broadcasting production where footage must be appropriately colorized in accordance with historical fact. In this article, we propose a practical video colorization framework that can easily reflect the user's intentions. The proposed framework uses a combination of two CNNs-a user-guided still-imagecolorization CNN and a color-propagation CNN-that allows the correction work to be performed efficiently. The user-guided still-image-colorization CNN produces key frames by colorizing several monochrome frames from the target video on the basis of user-specified colors and color-boundary information. The colorpropagation CNN automatically colorizes the entire video on the basis of the key frames, while suppressing discontinuous changes in color between frames. A quantitative evaluation showed that it is possible to produce color video reflecting the user's intention with less effort than with earlier methods.

show abstract

Section: Related Workmentioning

confidence: 99%

A Practical Monochrome Video Colorization Framework for Broadcast Program Production

Endo

Kawai

Mchizuki

2021

IEEE Trans. on Broadcast.

View full text Add to dashboard Cite

show abstract

“…As additional contribution in the thesis [Casaca 2014], we also propose new algorithms for image inpainting and photo colorization (see Figure 4 and the video 2 for illustrations). The methods rely on the accuracy of the proposed segmentation approaches to properly perform inpainting and image colorization, as reported in [Casaca 2014, Casaca et al 2015c, Casaca et al 2015a.…”

Section: Image Inpainting and Photo Colorizationmentioning

confidence: 99%

Graph Laplacian for Spectral Clustering and Seeded Image Segmentation

Casaca¹,

Taubin²,

Nonato³

2015

Anais Do XXVIII Concurso De Teses E Dissertações (CTD 2015)

Self Cite

View full text Add to dashboard Cite

Interactive segmentation methods have gained much attention lately, specially due to their good performance in segmenting complex images and easy utilization. However, most interactive segmentation algorithms rely on sophisticated mathematical formulations whose effectiveness highly depends on the kind of image to be processed. In fact, sharp adherence to the contours of image segments, uniqueness of solution, high computational burden, and extensive user interaction are some of the weaknesses of most existing methods. In this thesis we proposed two novel interactive image segmentation techniques that sort out the issues raised above. The proposed methods rely on Laplace operators, spectral graph theory, and optimization schemes towards enabling highly accurate segmentation tools which demand a reduced amount of user interaction while still being mathematically simple and computationally efficient. The good performance of our segmentation algorithms is attested by a comprehensive set of comparisons against representative state-of-the-art methods. As additional contribution, we have also proposed two new algorithms for inpainting and photo colorization, both of which rely on the accuracy of our segmentation apparatus

show abstract

“…Hua et al [17] interpret colorization from a gradient domain perspective and propose a framework with edge-preserving constraints that includes colorization among other tasks. Casaca et al [13] achieve sharp edges with a completely different approach: They first use the color scribbles to partition the image into segments and then propagate color according to segment labels. This approach also allows easy corrections by iterated user-interaction.…”

Section: Introductionmentioning

confidence: 99%

“…Luan et al [9], classify colorization methods as stroke-or example-based. In stroke-based methods [2], [9]- [13], the user manually specifies a small amount of color scribbles on a single image or a sequence of images. In contrast, example-based algorithms [1], [14]- [16] require one or multiple fully colored images that are similar to the grayscale image to be colorized.…”

Section: Introductionmentioning

confidence: 99%

Turning Diffusion-Based Image Colorization Into Efficient Color Compression

Peter

Kaufhold

Weickert

2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

The work of Levin et al. (2004) popularized stroke-based methods that add color to gray value images according to a small amount of user-specified color samples. Even though such reconstructions from sparse data suggest a possible use in compression, only few attempts were made so far in this direction. Diffusion-based compression methods pursue a similar idea: they store only few image pixels and inpaint the missing regions. Despite this close relation and a lack of diffusion-based color codecs, colorization ideas were so far only integrated into transform-based approaches such as JPEG. We address this missing link with two contributions. First, we show the relation between the discrete colorization of Levin et al. and continuous diffusion-based inpainting in the YCbCr color space. It decomposes the image into a luma (brightness) channel and two chroma (color) channels. Our luma-guided diffusion framework steers the diffusion inpainting in the chroma channels according to the structure in the luma channel. We show that making the luma-guided colorization anisotropic outperforms the method of Levin et al. significantly. Second, we propose a new luma preference codec that invests a large fraction of the bit budget into an accurate representation of the luma channel. This allows a high-quality reconstruction of color data with our colorization technique. Simultaneously, we exploit the fact that the human visual system is more sensitive to structural than to color information. Our experiments demonstrate that our new codec outperforms the state of the art in diffusion-based image compression and is competitive to transform-based codecs.

show abstract

Interactive Image Colorization Using Laplacian Coordinates

Cited by 12 publications

References 15 publications

A Practical Monochrome Video Colorization Framework for Broadcast Program Production

A Practical Monochrome Video Colorization Framework for Broadcast Program Production

Graph Laplacian for Spectral Clustering and Seeded Image Segmentation

Turning Diffusion-Based Image Colorization Into Efficient Color Compression

Contact Info

Product

Resources

About