Corel Corporation

Microsoft Technology Licensing, LLC

Candela Corporation

Bruce Justin Lindbloom

William David Sproule

Andrew Shaun Ivory

Nitin Suri

Tzong-Jhy Wang

Andrew William Fitzgibbon

Reinhard Sebastian Bernhard Nowozin

Jeremy Martin Jancsary

Douglas E Meisner

Michael Greenhalgh

Danyal Khashabi

Technologies for a single-pass process for enhancing video quality with temporal smoothing. The process may include providing for user overrides of automatically enhanced video/frame characteristics and providing substantially immediate previews of enhanced video frames to a user. The process may also include detecting a degree of shakiness in a portion of the video, and performing or recommending stabilization based on the detected shakiness.

Automatic video quality enhancement with temporal smoothing and user override

Image demosaicing is described, for example, to enable raw image sensor data, where image elements have intensity values in only one of three color channels, to be converted into a color image where image elements have intensity values in three color channels. In various embodiments a trained machine learning component is used to carry out demosaicing optionally in combination with denoising. In some examples the trained machine learning system comprises a cascade of trained regression tree fields. In some examples the machine learning component has been trained using pairs of mosaiced and demosaiced images where the demosaiced images have been obtained by downscaling natural color digital images. For example, the mosaiced images are obtained from the demosaiced images by subsampling according to one of a variety of color filter array patterns.

Image demosaicing

A method or computer program product for color selection in a color image, including operations or instructions for selecting a base color in a base color portion of a color image; computing a perceptual color difference between the base color and a respective second color in the color image; comparing the perceptual color difference to a tolerance; and, identifying whether the color difference satisfies the tolerance.

Color selection and/or matching in a color image

Technology for re-coloring a region of a color image including determining an original base color in a region of a color image; establishing at least one shading parameter in the region of the color image; and combining a new base color with the at least one shading parameter in the region of the color image thereby producing a re-colored region of the color image.

Re-coloring a color image

A system that provides automatic background analysis of a digital image or other media element makes a determination that the image or media element may benefit from correction, and prompts the user to use a correction feature of the system. In some implementations, the prompt itself can navigate the user to the controls for the correction feature. Accordingly, users are notified when they might benefit from correction, and they can be further led to discover a feature with which they may have previously been unfamiliar.

Automatic media edit inspector

An improved method is described for obtaining, processing and displaying information relating to the ability of a display system to render any candidate color. This method is comprised of a Gamut Signal Encoder which produces a signal that is separately processed by a Distance Encoder, a Distance Classifier and Color Encoder and a Gamut Test Encoder, thus providing three processed signals for assisting in the understanding of a display device's ability to render the color.

Growing community of inventors

Eden Prairie, MN, United States of America

Bruce Justin Lindbloom