Abstract: A system and method for single-image dehazing of natural images are provided herein. Embodiments of the method may include the following steps: dividing a natural image which include haze, into a plurality of image patches, wherein the image patches are sufficiently small so that pixels of the image patches exhibit one dimensional distributions in RGB color space, denoted color-lines; generating local image formation models for the pixels of the plurality of image patches, respectively, based on a relationship between the color-lines and the haze; calculating an offset of the color-lines from origin point of the respective local image formation models, for the image patches; and estimating scene transmission of the natural image, based on the calculated offsets.

Abstract: A computer implemented method for applying a numerical approximation of a convolution of image I as represented by hierarchical signals al of level l with filter f, said method including the steps of: generating a forward transformation by applying a convolution between al and kernel h1 for each level of hierarchy l and by down-sampling the result of convolved al and h1; generating a backward transformation by applying, for each level of hierarchy l, a convolution between kernel h2 and an up-sampled forward transformation and combining the result with a convolution of al with kernel g; and combining the forward transformation with the backward transformation, to yield â0 being an approximation of a convolution between a and f, wherein kernels h1, h1, and g are optimized kernels of filter f.

Abstract: A method for deriving a blur kernel from a blurred image is provided herein. The method may include the following steps: obtaining a blurred image B, being a product of a blur kernel k applied to an original image I; calculating f?(x)=Rd*P?(B)(x) for every angle ?, wherein R denotes an autocorrelation operator, P? denotes a projection operator of based on angle ?, and d denotes a one dimensional differentiation filter; estimating spectral power of the blur kernel based on a given support parameter; estimating the blur kernel k using a phase retrieval algorithm, based on the estimated spectral power of the blur kernel; updating the support parameters; and repeating the estimating of the spectral power, the estimating of the kernel and the updating of the support parameters in an iterative, to yield the blur kernel.

Abstract: A method and system (30) generates an output image (21) of increased pixel resolution from an input image (20), which is non-dyadically upscaled to generate an upscaled image (22) having more pixels than the input image and is low-pass filtered to generate a smoothed image (23). A high detail image (24) is generated by subtraction and for each pixel in the upscaled image, a patch (25) containing the pixel is identified. A best-fit patch (26) within a localized region (27) of the smoothed image is found by searching in the smoothed image in close proximity to a mapped location of the patch in the upscaled image. Each pixel in the patch of the upscaled image is corrected by uniquely adding the value of the corresponding pixel in an equivalent patch of the high detail image corresponding to the best-fit patch, and the corrected upscaled image is stored for further processing.

Abstract: A computer implemented method for A computer implemented method for applying a numerical approximation of a convolution of image I as represented by hierarchical signals al of level l with filter f, said method including the steps of: generating a forward transformation by applying a convolution between al and kernel h1 for each level of hierarchy l and by down-sampling the result of convolved al and h1; generating a backward transformation by applying, for each level of hierarchy l, a convolution between kernel h2 and an up-sampled forward transformation and combining the result with a convolution of al with kernel g; and combining the forward transformation with the backward transformation, to yield â0 being an approximation of a convolution between a and f, wherein kernels h1, h1, and g are optimized kernels of filter f.

Abstract: A method for deriving a blur kernel from a blurred image is provided herein. The method may include the following steps: obtaining a blurred image B, being a product of a blur kernel k applied to an original image I; calculating f?(x)=Rd*P?(B)(x) for every angle ?, wherein R denotes an autocorrelation operator, P? denotes a projection operator of based on angle ?, and d denotes a one dimensional differentiation filter; estimating spectral power of the blur kernel based on a given support parameter; estimating the blur kernel k using a phase retrieval algorithm, based on the estimated spectral power of the blur kernel; updating the support parameters; and repeating the estimating of the spectral power, the estimating of the kernel and the updating of the support parameters in an iterative, to yield the blur kernel.

Abstract: A method, apparatus and computer program product are provided for recovering a haze-free image given a single input image. The method may include receiving a single input image I, wherein the input image is made up of a plurality of pixels. A surface radiance vector J of the input image I may be modeled as a product of a surface albedo coefficient R and a shading factor l. The method may further include determining, for each of the plurality of pixels, a value of a transmission t of the pixel, such that a covariance C? between the transmission t and the shading factor l is minimized, and recovering the surface radiance vector J based at least in part on the determined value of the transmission t for each pixel.

Abstract: A method and system (30) generates an output image (21) of increased pixel resolution from an input image (20), which is non-dyadically upscaled to generate an upscaled image (22) having more pixels than the input image and is low-pass filtered to generate a smoothed image (23). A high detail image (24) is generated by subtraction and for each pixel in the upscaled image, a patch (25) containing the pixel is identified. A best-fit patch (26) within a localized region (27) of the smoothed image is found by searching in the smoothed image in close proximity to a mapped location of the patch in the upscaled image. Each pixel in the patch of the upscaled image is corrected by uniquely adding the value of the corresponding pixel in an equivalent patch of the high detail image corresponding to the best-fit patch, and the corrected upscaled image is stored for further processing.

Abstract: Systems, methods, and techniques are provided for performing any one or more of edge-preserving image sharpening, edge-preserving image smoothing, edge-preserving image dynamic range compression, and edge-aware data interpolation on digital images, wherein a pixel prediction module is adapted for coupling to a memory storing pixel data representative of a digital image and extracts from the image predicted pixel values using robust smoothing. The predicted pixels are stored in a memory and respective detail values equal to the difference between respective original and predicted values are computed. A pixel update module computes approximation values by averaging the respective detail values with original pixel values using robust smoothing, and stores the approximation values for subsequent rendering.

Abstract: A method, apparatus and computer program product are provided for recovering a haze-free image given a single input image. The method may include receiving a single input image I, wherein the input image is made up of a plurality of pixels. A surface radiance vector J of the input image I may be modeled as a product of a surface albedo coefficient R and a shading factor l. The method may further include determining, for each of the plurality of pixels, a value of a transmission t of the pixel, such that a covariance C? between the transmission t and the shading factor l is minimized, and recovering the surface radiance vector J based at least in part on the determined value of the transmission t for each pixel.

Abstract: Systems, methods, and techniques are provided for performing any one or more of edge-preserving image sharpening, edge-preserving image smoothing, edge-preserving image dynamic range compression, and edge-aware data interpolation on digital images, wherein a pixel prediction module is adapted for coupling to a memory storing pixel data representative of a digital image and extracts from the image predicted pixel values using robust smoothing. The predicted pixels are stored in a memory and respective detail values equal to the difference between respective original and predicted values are computed. A pixel update module computes approximation values by averaging the respective detail values with original pixel values using robust smoothing, and stores the approximation values for subsequent rendering.

Abstract: Method and system for efficiently controlling animated smoke which utilizes a sequence of target smoke states to generate a smoke simulation in which the smoke is driven towards each of these targets in turn, while exhibiting natural-looking interesting smoke-like behavior. This control is made possible by two new terms added to standard flow equations: (i) a driving force term that causes the fluid to carry the smoke towards a particular target, and (ii) a smoke gathering term that prevents the smoke from diffusing too much. These terms are explicitly defined by the instantaneous state of the system at each simulation time step. Thus, no expensive optimization is required, allowing complex smoke animations to be generated with very little additional cost compared to ordinary flow simulations. The invention is also applicable to animation of other fluid flow phenomena.

Abstract: A gradient domain compression system generates, from an input image having a high luminance dynamic range, an output image having a lower luminance dynamic range. The system comprises a gradient image generator module, a gradient compression module, and an output image generator module. The gradient image generator module is configured to generate, from the input image, a gradient image representing, for respective points of the input image, gradient values in the luminance of the input image. The gradient compression module is configured to receive the gradient image and generate a compressed range gradient image in which the range of gradient values are compressed. The output image generator module is configured to receive the compressed range gradient image and to generate therefrom an image, the image generated by the output image generator module comprising the output image.

Abstract: A gradient domain compression system generates, from an input image having a high luminance dynamic range, an output image having a lower luminance dynamic range. The system comprises a gradient image generator module, a gradient compression module, and an output image generator module. The gradient image generator module is configured to generate, from the input image, a gradient image representing, for respective points of the input image, gradient values in the luminance of the input image. The gradient compression module is configured to receive the gradient image and generate a compressed range gradient image in which the range of gradient values are compressed. The output image generator module is configured to receive the compressed range gradient image and to generate therefrom an image, the image generated by the output image generator module comprising the output image.

Abstract: Method and system for efficiently controlling animated smoke which utilizes a sequence of target smoke states to generate a smoke simulation in which the smoke is driven towards each of these targets in turn, while exhibiting natural-looking interesting smoke-like behavior. This control is made possible by two new terms added to standard flow equations: (i) a driving force term that causes the fluid to carry the smoke towards a particular target, and (ii) a smoke gathering term that prevents the smoke from diffusing too much. These terms are explicitly defined by the instantaneous state of the system at each simulation time step. Thus, no expensive optimization is required, allowing complex smoke animations to be generated with very little additional cost compared to ordinary flow simulations. The invention is also applicable to animation of other fluid flow phenomena.