Image-based models for computer graphics lack resolution independence: they cannot be zoomed much beyond the pixel resolution they were sampled at without a degradation of quality. Interpolating images usually results in a blurring of edges and image details. We describe image interpolation algorithms which use a database of training images to create plausible high-frequency details in zoomed images. Image pre-processing steps allow the use of image detail from regions of the training images which may look quite different from the image to be processed. These methods preserve fine details, such as edges, generate believable textures, and can give good results even after zooming multiple octaves.

We propose a new definition of the total variation norm for vector valued functions which can be applied to restore color and other vector valued images. The new TV norm has the desirable properties of (i) not penalizing discontinuities (edges) in the image, (ii) rotationally invariant in the image space, and (iii) reduces to the usual TV norm in the scalar case. Some numerical experiments on denoising simple color images in RGB color space are presented. 1 Introduction During gathering and transfer of image data some noise and blur is usually introduced into the image. Several reconstruction methods based on the total variation (TV) norm have been proposed and studied for intensity (gray scale) images, see [9, 14, 21, 26, 29]. Since these methods have been successful in reducing noise and blur without smearing sharp edges for intensity images, it is natural to extend the TV norm to handle color and other vector valued images. Why do we need color restoration? It can be argued that si...

in the area of digital color imaging. In order to establish the background and lay down terminology, fundamental concepts of color perception and measurement are first presented using vector-space notation and terminology. Present-day color recording and reproduction systems are reviewed along with the common mathematical models used for representing these devices. Algorithms for processing color images for display and communication are surveyed, and a forecast of research trends is attempted. An extensive bibliography is provided. I.

A new method named STM is described for determining distance of objects and rapid autofocusing of camera systems. STM uses image defocus information and is based on a new Spatial-Domain Convolution/Deconvolution Transform. The method requires only two images taken with dierent camera parameters such as lens position, focal length, and aperture diameter. Both images can be arbitrarily blurred and neither of them needs to be a focused image. Therefore STM is very fast in comparison with Depth-from-Focus methods which search for the lens position or focal length of best focus. The method involves simple local operations and can be easily implemented in parallel to obtain the depthmap of a scene. STM has been implemented on an actual camera system named SPARCS. Experiments on the performance of STM and their results on realworld planar objects are presented. The results indicate that the accuracy of STM compares well with Depth-from-Focus methods and is useful in practical ap...

A new method is described for recovering the distance of objects in a scene from images formed by lenses. The recovery is based on measuring the change in the scene's image due to a known change in the three intrinsic camera parameters: (i) distance between the lens and the image detector, (ii) focal length of the lens, and (iii) diameter of the lens aperture. The method is parallel involving simple local computations. In comparison with stereo vision and structure-frommotion methods, the correspondence problem does not arise. This method for depth-map recovery may also be used for (i) obtaining focused images (i.e. images having large depth of field) from two images having finite depth of field, and (ii) rapid autofocusing of computer controlled video cameras. 1. Introduction Here we describe a new passive ranging method which in principle is fast and involves relatively weak assumptions that are generally valid. The method is basically a generalized version of the `depth-from-focu...

We use the paraxial geometric optics model of image formation to derive a set of camera focusing techniques. These techniques do not require calibration of cameras but involve a search of the camera parameter space. The techniques are proved to be theoretically sound. They include energy maximization of unltered, low-pass ltered, highpass ltered, and band-pass ltered images. It is shown that in the presence of high spatial frequencies, noise, and aliasing, focusing techniques based on band-pass lters perform well. The focusing techniques are implemented on a a prototype camera system named SPARCS. The architecture of SPARCS is described briey. The performance of the dierent techniques are compared experimentally. All techniques are found to perform well. One of them which has better overall characteristics is recommended for practical applications. 1 Introduction Focusing cameras is an important problem in computer vision and microscopy. In this paper we consider only those pas...

In order to work well, many computer vision algorithms require that their parameters be adjusted according to the image noise level, making it an important quantity to estimate. We show how to estimate an upper bound on the noise level from a single image based on a piecewise smooth image prior model and measured CCD camera response functions. We also learn the space of noise level functions– how noise level changes with respect to brightness–and use Bayesian MAP inference to infer the noise level function from a single image. We illustrate the utility of this noise estimation for two algorithms: edge detection and featurepreserving smoothing through bilateral filtering. For a variety of different noise levels, we obtain good results for both these algorithms with no user-specified inputs. 1.

When a band-pass filter is applied to a natural image, the distribution of the output has a consistent, distinctive form across many different images, with the distribution sharply peaked at zero and relatively heavy-tailed. This prior has been exploited for several image processing tasks. We show how this prior on the appearance of natural images can also be used to estimate full-resolution images from incomplete data. The unobserved image pixels are modeled with a factor graph. The constraints in the factor graph are based on the characteristic distribution of image derivatives. We introduce an efficient representation for finding candidate values for patches of the image being estimated, avoiding combinatorial explosion. The usefulness of this approach is demonstrated by applying it to two applications: extracting a high-resolution image from a low-resolution version and estimating a full-color image from an image with one color sample per pixel. We show how the super resolution system produces noticeably sharper images, with few significant artifacts. The demosaicing system produces full-color images with fewer color-fringing artifacts than images from other methods.

The image of a scene formed by an optical system such as a lens contains both photometric and geometric information about the scene. `Inverse Optics' is the problem of recovering this information from a set of images sensed by the camera. Previous solutions to this problem-- the depth-from-focusing methods-- required a large number (in principle, infinitely many) of images to be recorded and processed. Hence the methods were slow and computationally intensive. Recent work in this area suggests solutions that require only a few images and therefore are fast and computationally efficient. Here we present a coherent view of recent developments. Theoretical principles, practical issues, and unsolved problems are discussed. Preliminary experimental results are presented.

Image denoising algorithms often assume an additive white Gaussian noise (AWGN) process that is independent of the actual RGB values. Such approaches cannot effectively remove color noise produced by today’s CCD digital camera. In this paper, we propose a unified framework for two tasks: automatic estimation and removal of color noise from a single image using piecewise smooth image models. We introduce the noise level function (NLF), which is a continuous function describing the noise level as a function of image brightness. We then estimate an upper bound of the real NLF by fitting a lower envelope to the standard deviations of per-segment image variances. For denoising, the chrominance of color noise is significantly removed by projecting pixel values onto a line fit to the RGB values in each segment. Then, a Gaussian conditional random field (GCRF) is constructed to obtain the underlying clean image from the noisy input. Extensive experiments are conducted to test the proposed algorithm, which is shown to outperform state-of-the-art denoising algorithms.