It is demonstrated that in cases, such as those above, the available high resolution input image may be leveraged as a prior in the context of a joint bilateral upsampling procedure to produce a better high resolution solution.
Abstract:
Image analysis and enhancement tasks such as tone mapping, colorization, stereo depth, and photomontage, often require computing a solution (e.g., for exposure, chromaticity, disparity, labels) over the pixel grid. Computational and memory costs often require that a smaller solution be run over a downsampled image. Although general purpose upsampling methods can be used to interpolate the low resolution solution to the full resolution, these methods generally assume a smoothness prior for the interpolation. We demonstrate that in cases, such as those above, the available high resolution input image may be leveraged as a prior in the context of a joint bilateral upsampling procedure to produce a better high resolution solution. We show results for each of the applications above and compare them to traditional upsampling methods.
TL;DR: The guided filter is a novel explicit image filter derived from a local linear model that can be used as an edge-preserving smoothing operator like the popular bilateral filter, but it has better behaviors near edges.
TL;DR: The guided filter is demonstrated that it is both effective and efficient in a great variety of computer vision and computer graphics applications including noise reduction, detail smoothing/enhancement, HDR compression, image matting/feathering, haze removal, and joint upsampling.
TL;DR: This thesis develops an effective but very simple prior, called the dark channel prior, to remove haze from a single image, and thus solves the ambiguity of the problem.
TL;DR: Whether you want to build simple or sophisticated vision applications, Learning OpenCV is the book any developer or hobbyist needs to get started, with the help of hands-on exercises in each chapter.
TL;DR: The current comprehensive survey provides an overview of most of these published works by grouping them in a broad taxonomy, and common issues in super-resolution algorithms, such as imaging models and registration algorithms, optimization of the cost functions employed, dealing with color information, improvement factors, assessment of super- resolution algorithms, and the most commonly employed databases are discussed.
TL;DR: In contrast with filters that operate on the three bands of a color image separately, a bilateral filter can enforce the perceptual metric underlying the CIE-Lab color space, and smooth colors and preserve edges in a way that is tuned to human perception.
TL;DR: This paper has designed a stand-alone, flexible C++ implementation that enables the evaluation of individual components and that can easily be extended to include new algorithms.
TL;DR: This work presents two algorithms based on graph cuts that efficiently find a local minimum with respect to two types of large moves, namely expansion moves and swap moves that allow important cases of discontinuity preserving energies.
TL;DR: A new technique for the display of high-dynamic-range images, which reduces the contrast while preserving detail, is presented, based on a two-scale decomposition of the image into a base layer.
TL;DR: A new technique for the display of high-dynamic-range images, which reduces the contrast while preserving detail, is presented, based on a two-scale decomposition of the image into a base layer, encoding large-scale variations, and a detail layer.
Q1. What contributions have the authors mentioned in the paper "Joint bilateral upsampling" ?
The authors demonstrate that in cases, such as those above, the available high resolution input image may be leveraged as a prior in the context of a joint bilateral upsampling procedure to produce a better high resolution solution. The authors show results for each of the applications above and compare them to traditional upsampling methods.
Q2. What did the authors use to compute the errors?
To compute the errors, the authors computed a full resolution solution (or simply used the full resolution color image or depth map for colorization and stereo depth) as ground truth.
Q3. What is the performance of the technique?
The performance is proportional to the output size and not to the upsampling factor, because the domain filter is always applied to the low resolution solution.
Q4. What is the filtered result for a position p?
More formally, for some position p, the filtered result is:Jp = 1 kp ∑ q∈Ω Iq f (||p−q||) g(||Ip − Iq||), (1)where f is the spatial filter kernel, such as a Gaussian centered over p, and g is the range filter kernel, centered at the image value at p.
Q5. What is the method used to upsample a low resolution image?
Their method estimates an alignment mapping, and then uses warping and fill-in from neighboring movie frames to upsample the low-resolution image.
Q6. What is the problem with the upsampling of high resolution images?
Such high resolutions pose a difficult challenge for the methods cited above, which typically require at least linear time and, more importantly, linear space to compute a global solution.
Q7. What is the way to upsample a low resolution image?
Given a high resolution image, Ĩ, and a low resolution solution, S, computed for a downsampled version of the image, the authors propose a simple method that applies a joint bilateral filter to upsample the solution.
Q8. What is the effect of the filter on the relative improvement?
Their filter performed well at all downsampling levels, and, as expected, the relative improvement increased with each additional level of down sampling.
Q9. What is the purpose of stereo matching?
Stereo Depth: Stereo matching is a fundamental task in image analysis, whose goal is to determine the disparities between pairs of corresponding pixels in two or more images.
Q10. What is the way to use the UI?
Since some of the applications require some UI, you need enough image left to, for example, scribble on the hints for tone mapping or colorization.
Q11. What is the difference between upsampling and resampling?
Images upsampled in this manner typically suffer from blurring of sharp edges, because of the smoothness prior inherent in the linear interpolation filters.