Yissum Research Development Company of the Hebrew University of Jerusalem Ltd.

Microsoft Technology Licensing, LLC

Adobe, Inc.

Briefcam Ltd.

Daniel Lischinski

Michael F Cohen

Raanan Fattal

Johannes Peter Kopf

Matthieu Tony Uyttendaele

Michael Werman

Zeev Farbman

Elya Shechtman

Matthew Uyttendaele

Daniel Goldman

Shmuel Peleg

Johannes P Kopf

Yoav HaCohen

Alexander Rav-Acha

Anat Levin

Yair Weiss

Liad Kaufman

A computer implemented method for applying a numerical approximation of a convolution of image I as represented by hierarchical signals aof level l with filter f, said method including the steps of: generating a forward transformation by applying a convolution between aand kernel hfor each level of hierarchy l and by down-sampling the result of convolved aand h; generating a backward transformation by applying, for each level of hierarchy l, a convolution between kernel hand an up-sampled forward transformation and combining the result with a convolution of awith kernel g; and combining the forward transformation with the backward transformation, to yield &#xe2;being an approximation of a convolution between a and f, wherein kernels h, h, and g are optimized kernels of filter f.

Applying rapid numerical approximation of convolutions with filters for image processing purposes

A method and apparatus for enhancing a digital photographic image uses a combination of global and content-specific operations. Image data is analyzed to detect one or more content items in the image to be separately enhanced. Then a content-specific enhancement operation is performed on data representing at least one detected content item, separately from the remainder of the image data. Several such content-specific operations may be performed for different types of content item. The content-specific enhancement operation comprises manipulating data, and the manipulation applies different adjustments to different pixels in the detected content item and the determination of the adjustments is based solely on analysis of the image data. Then a different enhancement operation is performed on at least the remaining image data excluding said one or more detected content items.

Method and apparatus for enhancing a digital photographic image

A method of tonally stabilizing a video sequence is provided herein. The method includes the following stages: automatically selecting one or more anchor frames from a sequence of frames; obtaining an anchor adjustment map for each selected anchor frame; applying an edge-preserving smoothing algorithm to the sequence of frames; generating for any given pair of smoothed frames, a robust set of pixels indicating pixels affected by external tonal fluctuation only; initializing an adjustment map for any given frame by applying the anchor adjustment map to accumulated color differences between pixels of the robust set of the given frame and the anchor frame; and completing the initialized adjustment map by predicting values of pixels in each adjustment map not included in the robust set by applying an interpolation at a color space for these pixels, wherein the adjustment maps are usable for tonally aligning the video sequence with the anchor frame.

Tonal stabilization of video

Non-rigid dense correspondence (NRDC) for image enhancement may be performed. In one embodiment, a correspondence may be computed for each one of a plurality of regions of a source image to one of a plurality of regions of a reference image. Computing the correspondences may include searching within a search range for each of a plurality of image characteristics. One or more of the correspondences may be aggregated into matched regions. A global color transform and/or deblurring may be applied to the source image. In one embodiment, the global color transform and/or deblurring may be based on the matched regions. At least one of the search ranges may optionally be adjusted. In some embodiments, computing, aggregating, applying and/or deblurring, and adjusting may be iteratively performed.

Non-rigid dense correspondence

A novel image view may be synthesized using a three-dimensional reference model. In an example embodiment, a device-implemented method for synthesizing a novel image view includes acts of registering, selecting, applying and synthesizing. An image is registered to at least one reference model. A source block of visual data from the image is selected with regard to a destination block of the reference model based on a source depth associated with the source block and a destination depth associated with the destination block. The destination position of the destination block of the reference model is not visible in the image. The source block of visual data from the image is applied to the destination block of the reference model to produce an image-augmented model. A novel image view is synthesized using the image-augmented model.

Image view synthesis using a three-dimensional reference model

An image may be dehazed using a three-dimensional reference model. In an example embodiment, a device-implemented method for dehazing includes acts of registering, estimating, and producing. An image that includes haze is registered to a reference model. A haze curve is estimated for the image based on a relationship between colors in the image and colors and depths of the reference model. A dehazed image is produced by using the estimated haze curve to reduce the haze of the image.

Dehazing an image using a three-dimensional reference model

A 'Joint Bilateral Upsampler' uses a high-resolution input signal to guide the interpolation of a low-resolution solution set (derived from a downsampled version of the input signal) from low-to high-resolution. The resulting high-resolution solution set is then saved or applied to the original input signal to produce a high-resolution output signal. The high-resolution solution set is close to what would be produced directly from the input signal without downsampling. However, since the high-resolution solution set is constructed in part from a downsampled version of the input signal, it is computed using significantly less computational overhead and memory than a solution set computed directly from a high-resolution signal. Consequently, the Joint Bilateral Upsampler is advantageous for use in near real-time operations, in applications where user wait times are important, and in systems where computational costs and available memory are limited.

Joint bilateral upsampling

A computer-implemented method and system for transforming a first sequence of video frames of a first dynamic scene captured at regular time intervals to a second sequence of video frames depicting a second dynamic scene wherein for at least two successive frames of the second sequence, there are selected from at least three different frames of the first sequence portions that are spatially contiguous in the first dynamic scene and copied to a corresponding frame of the second sequence so as to maintain their spatial continuity in the first sequence. In a second aspect, for at least one feature in the first dynamic scene respective portions of the first sequence of video frames are sampled at a different rate than surrounding portions of the first sequence of video frames; and the sampled portions are copied to a corresponding frame of the second sequence.

Method and system for spatio-temporal video warping

In a method and system for matting a foreground object F having an opacity &#x3b1; constrained by associating a characteristic with selected pixels in an image having a background B, weights are determined for all edges of neighboring pixels for the image and used to build a Laplacian matrix L. The equation &#x3b1; is solved where &#x3b1;=arg min &#x3b1;L&#x3b1; s.t.&#x3b1;=s, &#x2200;i&#x3b5;S, S is the group of selected pixels, and sis the value indicated by the associated characteristic. The equation I=&#x3b1;F+(1&#x2212;&#x3b1;)Bis solved for F and B with additional smoothness assumptions on F and B; after which the foreground object F may be composited on a selected background B' that may be the original background B or may be a different background, thus allowing foreground features to be extracted from the original image and copied to a different background.

Closed form method and system for matting a foreground object in an image having a background

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.

Method and system for performing computer graphic simulation of a fluid using target-driven control

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.

Growing community of inventors

Jerusalem, Israel

Daniel Lischinski