Patents by Inventor Thomas Nicolas Emmanuel Veit
Thomas Nicolas Emmanuel Veit has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20200177786Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.Type: ApplicationFiled: February 3, 2020Publication date: June 4, 2020Inventors: Guillaume Matthieu Guerin, Antoine Regimbeau, Thomas Nicolas Emmanuel Veit, Bruno Cesar Douady-Pleven, Violaine Marie Mong-lan Sudret
-
Publication number: 20200151854Abstract: Implementations disclosed herein include an image capture device, a system, and a method for performing multiscale denoising of a video. An image processor of the image capture device obtains a video frame. The video frame may be in any format and may include noise artifacts. The image processor decomposes the video frame into one or more sub-frames. In some implementations, the image processor denoises each of the one or more sub-frames. The image processor decomposes one or more video frames in a temporal buffer into one or more temporal sub-frames. The image processor denoises each of the temporal sub-frames. The image processor reconstructs the one or more denoised sub-frames and the one or more temporal sub-frames to produce a denoised video frame. A memory of the image capture device may be configured to store the denoised video frame.Type: ApplicationFiled: November 9, 2018Publication date: May 14, 2020Inventors: Matias Tassano Ferrés, Thomas Nicolas Emmanuel Veit, Julie Delon
-
Patent number: 10643308Abstract: Systems and methods are disclosed for non-local means denoising of images. For example, methods may include receiving an image from an image sensor; determining a set of non-local means weights for the image; applying the set of non-local means weights to the image to obtain a first denoised image; applying the set of non-local means weights to the first denoised image to obtain a second denoised image; and storing, displaying, or transmitting an output image based on the second denoised image.Type: GrantFiled: October 11, 2017Date of Patent: May 5, 2020Assignee: GoPro, Inc.Inventors: Bruno César Douady-Pleven, Thomas Nicolas Emmanuel Veit, Marc Lebrun
-
Patent number: 10630921Abstract: Image signal processing may include flare reduction, which may include obtaining a first input frame captured by a first image capture device of an image capture apparatus, the first image capture device having a first field-of-view, and the first input frame including lens flare corresponding to a primary light source; obtaining a second input frame captured by a second image capture device of the image capture apparatus, the second image capture device having a second field-of-view partially overlapping the first field-of-view; obtaining primary light source information corresponding to the primary light source based on the first input frame and the second input frame; obtaining a processed frame by modifying the first input frame based on the primary light source information to minimize the lens flare; and outputting the processed frame.Type: GrantFiled: May 21, 2018Date of Patent: April 21, 2020Assignee: GoPro, Inc.Inventors: Bruno César Douady-Pleven, Nicolas Boehrer, Thomas Nicolas Emmanuel Veit
-
Publication number: 20200098098Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include accessing an image from an image sensor; detecting an object area on the image; classifying the object area on the image; applying a filter to an object area of the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.Type: ApplicationFiled: September 20, 2018Publication date: March 26, 2020Inventors: Heng Zhang, Thomas Nicolas Emmanuel Veit, Guillaume Matthieu Guérin
-
Patent number: 10554903Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.Type: GrantFiled: March 29, 2019Date of Patent: February 4, 2020Assignee: GoPro, Inc.Inventors: Guillaume Matthieu Guerin, Antoine Regimbeau, Thomas Nicolas Emmanuel Veit, Bruno César Douady-Pleven, Violaine Marie Mong-lan Sudret
-
Patent number: 10530995Abstract: A system accesses an image with each pixel of the image having luminance values each representative of a color component of the pixel. The system generates a first histogram for aggregate luminance values of the image, and accesses a target histogram for the image representative of a desired global image contrast. The system computes a transfer function based on the first histogram and the target histogram such that when the transfer function is applied, a histogram of the modified aggregate luminance values is within a threshold similarity of the target histogram. The system modifies the image by applying the transfer function to the luminance values of the image to produce a tone mapped image, and outputs the modified image.Type: GrantFiled: November 22, 2017Date of Patent: January 7, 2020Assignee: GoPro, Inc.Inventors: Bruno César Douady-Pleven, Michael Serge Andre Kraak, Guillaume Matthieu Guérin, Thomas Nicolas Emmanuel Veit
-
Publication number: 20190355098Abstract: Implementations disclosed herein include an image capture device, a system, and a method for performing multiscale denoising of an image. An image processor of the image capture device obtains a first image. The first image may be in any format and may include noise artifacts. The image processor decomposes the first image into one or more sub-images. The sub-images may range from a coarse scale to a fine scale. In some implementations, the image processor iteratively denoises each of the one or more sub-images from the coarse scale to the fine scale. The image processor reconstructs the one or more denoised sub-images to produce a denoised image. A memory of the image capture device may be configured to store the denoised image.Type: ApplicationFiled: May 18, 2018Publication date: November 21, 2019Inventors: Matias Tassano Ferrés, Thomas Nicolas Emmanuel Veit, Marc Lebrun, Julie Delon
-
Publication number: 20190356873Abstract: Image signal processing may include flare reduction, which may include obtaining a first input frame captured by a first image capture device of an image capture apparatus, the first image capture device having a first field-of-view, and the first input frame including lens flare corresponding to a primary light source; obtaining a second input frame captured by a second image capture device of the image capture apparatus, the second image capture device having a second field-of-view partially overlapping the first field-of-view; obtaining primary light source information corresponding to the primary light source based on the first input frame and the second input frame; obtaining a processed frame by modifying the first input frame based on the primary light source information to minimize the lens flare; and outputting the processed frame.Type: ApplicationFiled: May 21, 2018Publication date: November 21, 2019Inventors: Bruno César Douady-Pleven, Nicolas Boehrer, Thomas Nicolas Emmanuel Veit
-
Publication number: 20190230274Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.Type: ApplicationFiled: March 29, 2019Publication date: July 25, 2019Inventors: Guillaume Matthieu Guerin, Antoine Regimbeau, Thomas Nicolas Emmanuel Veit, Bruno César Douady-Pleven, Violaine Marie Mong-lan Sudret
-
Patent number: 10284785Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.Type: GrantFiled: August 30, 2017Date of Patent: May 7, 2019Assignee: GoPro, Inc.Inventors: Guillaume Matthieu Guerin, Antoine Regimbeau, Thomas Nicolas Emmanuel Veit, Bruno Cesar Douady-Pleven, Violaine Marie Mong-lan Sudret
-
Publication number: 20190108622Abstract: Systems and methods are disclosed for non-local means denoising of images. For example, methods may include receiving an image from an image sensor; determining a set of non-local means weights for the image; applying the set of non-local means weights to the image to obtain a first denoised image; applying the set of non-local means weights to the first denoised image to obtain a second denoised image; and storing, displaying, or transmitting an output image based on the second denoised image.Type: ApplicationFiled: October 11, 2017Publication date: April 11, 2019Inventors: Bruno César Douady-Pleven, Thomas Nicolas Emmanuel Veit, Marc Lebrun
-
Publication number: 20190098274Abstract: Image signal processing may include desaturation control, which may include adaptive desaturation control. Image signal processing with desaturation control may include obtaining, by an image signal processor, from an image sensor, an input image signal representing an input image, obtaining, by the image signal processor, color correction information for the input image, obtaining a color corrected image based on the input image using color correction with desaturation control such that inaccurate colorization of the color corrected image is minimized, and outputting the color corrected image.Type: ApplicationFiled: July 24, 2018Publication date: March 28, 2019Inventors: Bruno César Douady-Pleven, Thomas Nicolas Emmanuel Veit, Marc Lebrun
-
Publication number: 20190068865Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.Type: ApplicationFiled: August 30, 2017Publication date: February 28, 2019Inventors: Guillaume Matthieu Guerin, Antoine Regimbeau, Thomas Nicolas Emmanuel Veit, Bruno Cesar Douady-Pleven, Violaine Marie Mong-lan Sudret
-
Publication number: 20180211413Abstract: Obtaining color adjusted image portions using sub-three-dimensional look-up tables may include obtaining the color adjusted image portion by obtaining a value for an input image portion wherein the value includes a first parameter, a second parameter, and a third parameter, obtaining a color adjusted first parameter from at least a first one-dimensional look-up table based on the first parameter, the second parameter, and the third parameter, obtaining a color adjusted second parameter from at least a second one-dimensional look-up table based on the first parameter, the second parameter, and the third parameter, obtaining a color adjusted third parameter from at least a third one-dimensional look-up table based on the first parameter, the second parameter, and the third parameter, and outputting the color adjusted image portion based on a combination of the color adjusted first parameter, the color adjusted second parameter, and the color adjusted third parameter.Type: ApplicationFiled: February 22, 2017Publication date: July 26, 2018Inventors: Thomas Nicolas Emmanuel Veit, Bruno Cesar Douady-Pleven, Guillaume Matthieu Guérin
-
Patent number: 10007967Abstract: A system access a reference frame and temporally adjacent frames. For each portion of the reference image frame, the system calculates a pixel distance value between the portion of the reference image frame and a corresponding portion of each temporally adjacent image frame. If the pixel distance value indicates a potential ghosting artifact, the system computes a set of spatial noise reduction values for the image portion. Otherwise, the system computes a set of temporal noise reduction values for the image portion. The system blends the sets of computed spatial noise reduction values and the sets of computed temporal noise reduction values, and generates a modified reference image frame based on the blended set of noise reduction values.Type: GrantFiled: March 25, 2016Date of Patent: June 26, 2018Assignee: GoPro, Inc.Inventors: Bruno Cesar Douady-Pleven, Michael Serge André Kraak, Guillaume Matthieu Guerin, Thomas Nicolas Emmanuel Veit
-
Publication number: 20180097992Abstract: A system accesses an image with each pixel of the image having luminance values each representative of a color component of the pixel. The system generates a first histogram for aggregate luminance values of the image, and accesses a target histogram for the image representative of a desired global image contrast. The system computes a transfer function based on the first histogram and the target histogram such that when the transfer function is applied, a histogram of the modified aggregate luminance values is within a threshold similarity of the target histogram. The system modifies the image by applying the transfer function to the luminance values of the image to produce a tone mapped image, and outputs the modified image.Type: ApplicationFiled: November 22, 2017Publication date: April 5, 2018Inventors: Bruno César Douady-Pleven, Michael Serge Andre Kraak, Guillaume Matthieu Guérin, Thomas Nicolas Emmanuel Veit
-
Patent number: 9842381Abstract: A system accesses an image with each pixel of the image having luminance values each representative of a color component of the pixel. The system generates a first histogram for aggregate luminance values of the image, and accesses a target histogram for the image representative of a desired global image contrast. The system computes a transfer function based on the first histogram and the target histogram such that when the transfer function is applied, a histogram of the modified aggregate luminance values is within a threshold similarity of the target histogram. The system modifies the image by applying the transfer function to the luminance values of the image to produce a tone mapped image, and outputs the modified image.Type: GrantFiled: March 25, 2016Date of Patent: December 12, 2017Assignee: GoPro, Inc.Inventors: Bruno Cesar Douady-Pleven, Michael Serge André Kraak, Guillaume Matthieu Guerin, Thomas Nicolas Emmanuel Veit
-
Patent number: 9754349Abstract: A system determines for each color channel of each portion of the image, a corresponding adjustment value to apply to the color channel to correct for a color irregularity. The system determines a corrected adjustment value based on a difference between twice the pixel value and the maximum saturation value. If the adjustment value as applied is larger than the corrected adjustment value, the system applies the adjustment value to the corresponding color channel of the image portion to produce the adjusted color channel. Otherwise, the system applies the corrected adjustment to the corresponding color channel of the image portion to produce an adjusted color channel. The system generates a modified image based on the adjusted color channel.Type: GrantFiled: March 25, 2016Date of Patent: September 5, 2017Assignee: GoPro, Inc.Inventors: Bruno Cesar Douady-Pleven, Michael Serge André Kraak, Guillaume Matthieu Guerin, Thomas Nicolas Emmanuel Veit
-
Patent number: 9659349Abstract: A system identifies a scaling position in a captured image, and identifies red subpixels adjacent to the scaling position. The system computes a scaled red subpixel for the scaling position based on the identified red subpixels according to constraints. The system further computes a scaled blue subpixel based on identified adjacent blue subpixels, according to constraints, and computes a scaled green subpixel position based on Gr and Gb subpixels adjacent to the scaling position according to certain constraints. The system then generates a scaled image representative of the captured image, the scaled image including at least the scaled red subpixel value, the scaled blue subpixel value, and the scaled green subpixel value.Type: GrantFiled: March 25, 2016Date of Patent: May 23, 2017Assignee: GoPro, Inc.Inventors: Bruno Cesar Douady-Pleven, Michael Serge André Kraak, Guillaume Matthieu Guerin, Thomas Nicolas Emmanuel Veit