Two-scale tone management for photographic look

Bae, Soonmin; Paris, Sylvain; Durand, Frédo

doi:10.1145/1141911.1141935

Cited by 315 publications

(192 citation statements)

References 27 publications

Supporting

Mentioning

192

Contrasting

Order By: Relevance

“…Appearance editing includes a broad variety of applications, such as color manipulation [2,27], detail reduction/enhancement [4,12], and non-photorealistic stylization [6,32]. Whereas these effects were formerly applied to all of the pixels in an image, owing to the limitation of computational resources, it is currently possible to control these effects by specifying edit intentions with a small number of strokes.…”

Section: Related Workmentioning

confidence: 99%

Sparse pixel sampling for appearance edit propagation

Yatagawa

Yamaguchi

2015

Vis Comput

View full text Add to dashboard Cite

Edit propagation is an appearance-editing method using sparsely provided edit strokes from users. Although edit propagation has a wide variety of applications, it is computationally complex, owing to the need to solve large linear systems. To reduce the computational cost, interpolation-based approaches have been studied intensely. This study is inspired by an interpolation-based edit-propagation method that uses a clustering algorithm to determine samples. The method uses an interpolant, which approximates edit parameters with convex combinations of the samples. However, because the clustering algorithm generates samples that lie inside the set of pixels in a feature space, an interpolant with convex combinations does not allow for an exact reconstruction of the pixels outside the convex hull. To address this issue, this paper proposes a novel approximation model for interpolating image colors as well as edit parameters using affine combinations. In addition, this paper introduces sparse pixel sampling to determine the quantity and positions of samples and the weight coefficients of the affine combinations simultaneously. Sparse pixel sampling is performed by updating candidate pixels. Unnecessary pixels are discarded with compressive sensing, and new candidate pixels are greedily resampled following their approximation errors. This paper demonstrates that the B Tatsuya Yatagawa proposed model achieves better approximation in terms of both image colors and edit parameters, and discusses the properties of the proposed model with various experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

Sparse pixel sampling for appearance edit propagation

Yatagawa

Yamaguchi

2015

Vis Comput

View full text Add to dashboard Cite

show abstract

“…Distortion imposed by a steganography method on a textural image is less detectable by human vision system, and therefore such images are more suitable for steganography purpose. Use of appropriate features to measure the textureness of images [35] can guide the embedder to pick a proper cover image.…”

Section: Texturenessmentioning

confidence: 99%

Using contourlet transform and cover selection for secure steganography

Sajedi

Jamzad

2010

Int. J. Inf. Secur.

View full text Add to dashboard Cite

In this paper, we present a new adaptive contourlet-based steganography method that hides secret data in a specific or automatically selected cover image. Our proposed steganography method primarily decomposes the cover image by contourlet transform. Then, every bit of secret data is embedded by increasing or decreasing the value of one coefficient in a block of a contourlet subband. Contourlet coefficients are manipulated relative to their magnitudes to hide the secret data adaptively. In addition to proposing contourlet-based steganography method, this work investigates the effect of cover selection on steganography embedding and steganalysis results. We demonstrate, through the experiments, that choosing suitable cover image by a proper selection measure could help the steganographer reduce detectability of stego images. The proposed technique is examined with some state-of-the-art steganalysis methods, and the results illustrate that an image can successfully hide secret data with average embedding capacity of 0.02 bits per pixel in a random selected cover image. Cover selection improves the embedding capacity up to 0.06 bits per pixel. Several experiments and comparative studies are performed to show the effectiveness of the proposed technique in enhancing the security of stego images, as well as to demonstrate its gain over the previous approaches in literature.

show abstract

“…On Ground Truth In practical applications such as photograph enhancement (Bae et al 2006) or user-driven image editing (Weiss 2006), the notions of numerical accuracy and ground truth are not always well defined. Running times can be objectively measured, but other aspects are elusive and difficult to quantify.…”

Section: Evaluation Of Our Approximationmentioning

confidence: 99%

“…We refer the reader to the articles by Petschnigg et al (2004) and Eisemann and Durand (2004) for more advanced approaches to processing flash/no-flash pairs. Bae et al (2006) propose another use of the cross bilateral filter to estimate the local amount of texture in a picture. All the results of this article have been computed with our technique.…”

Section: Cross Bilateral Filtermentioning

confidence: 99%

“…It has been adopted for several applications such as image denoising (Tomasi and Manduchi 1998;Liu et al 2006), relighting and texture manipulation (Oh et al 2001), dynamic range compression (Durand and Dorsey 2002), illumination correction (Elad 2005), and photograph enhancement (Eisemann and Durand 2004;Petschnigg et al 2004;Bae et al 2006). It has also be adapted to other domains such as mesh fairing (Jones et al 2003;Fleishman et al 2003), volumetric denoising (Wong et al 2004), optical flow and motion estimation (Xiao et al 2006;Sand and Teller 2006), and video processing (Bennett and McMillan 2005;Winnemöller et al 2006).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach

2007

Self Cite

View full text Add to dashboard Cite

The bilateral filter is a nonlinear filter that smoothes a signal while preserving strong edges. It has demonstrated great effectiveness for a variety of problems in computer vision and computer graphics, and fast versions have been proposed. Unfortunately, little is known about the accuracy of such accelerations. In this paper, we propose a new signal-processing analysis of the bilateral filter which complements the recent studies that analyzed it as a PDE or as a robust statistical estimator. The key to our analysis is to express the filter in a higher-dimensional space where the signal intensity is added to the original domain dimensions. Importantly, this signal-processing perspective allows us to develop a novel bilateral filtering acceleration using downsampling in space and intensity. This affords a principled expression of accuracy in terms of bandwidth and sampling. The bilateral filter can be expressed as linear convolutions in this augmented space followed by two simple nonlinearities. This allows us to derive criteria for downsampling the key operations and achieving important acceleration of the bilateral filter. We show that, for the same running time, our method is more accurate than previous acceleration techniques. Typically, we are able to process a 2 megapixel image using our acceleration technique in less than a second, and have the result be visually similar to the exact computation that takes several tens of minutes. The acceleration is most effective with large spatial kernels. Furthermore, this approach extends naturally to color images and cross bilateral filtering.

show abstract

Two-scale tone management for photographic look

Cited by 315 publications

References 27 publications

Sparse pixel sampling for appearance edit propagation

Sparse pixel sampling for appearance edit propagation

Using contourlet transform and cover selection for secure steganography

A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach

Contact Info

Product

Resources

About