Patents by Inventor Aliakbar Darabi

Aliakbar Darabi 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: 20160364846
    Abstract: Embodiments described herein are directed to methods and systems for facilitating control of smoothness of transitions between images. In embodiments, a difference of color values of pixels between a foreground image and the background image are identified along a boundary associated with a location at which to paste the foreground image relative to the background image. Thereafter, recursive down sampling of a region of pixels within the boundary by a sampling factor is performed to produce a plurality of down sampled images having color difference indicators associated with each pixel of the down sampled images. Such color difference indicators indicate whether a difference of color value exists for the corresponding pixel. To effectuate a seamless transition, the color difference indicators are normalized in association with each recursively down sampled image.
    Type: Application
    Filed: May 20, 2016
    Publication date: December 15, 2016
    Inventors: SYLVAIN PARIS, SOHRAB AMIRGHODSI, ALIAKBAR DARABI, ELYA SHECHTMAN
  • Patent number: 9317773
    Abstract: Methods, apparatus, and computer-readable storage media for patch-based image synthesis using color and color gradient voting. A patch matching technique provides an extended patch search space that encompasses geometric and photometric transformations, as well as color and color gradient domain features. The photometric transformations may include gain and bias. The patch-based image synthesis techniques may also integrate image color and color gradients into the patch representation and replace conventional color averaging with a technique that performs voting for colors and color gradients and then solves a screened Poisson equation based on values for colors and color gradients when blending patch(es) with a target image.
    Type: Grant
    Filed: September 5, 2014
    Date of Patent: April 19, 2016
    Assignee: Adobe Systems Incorporated
    Inventors: Elya Shechtman, Daniel R. Goldman, Aliakbar Darabi
  • Patent number: 9311735
    Abstract: A region of an image on which a content aware fill operation is to be performed is identified by a device, the content aware fill operation replacing pixel values in the region based on pixel values from one or more other regions. The device generates a reduced-size version of the image by down sampling the image, and sends the reduced-size version of the image to a remote service. The remote service generates a mapping indicating which pixels in the reduced-size version of the image are to be used as the values of which other pixels in the region of the reduced-size version of the image. The mapping is compressed and returned to the device. The device decompresses the mapping and up samples the mapping. An output image is generated based on the originally obtained image, the up sampled mapping, and an indication of the region.
    Type: Grant
    Filed: November 21, 2014
    Date of Patent: April 12, 2016
    Assignee: Adobe Systems Incorporated
    Inventors: Sohrab Amirghodsi, Aliakbar Darabi, Elya Schectman
  • Publication number: 20150235399
    Abstract: Variable patch shape synthesis techniques are described. In one or more implementations, a plurality of patches are computed from one or more images, at least one of the plurality of patches having a different shape than another one of the plurality of patches. The shapes define an area to be considered for use in a patch synthesis technique. The patch synthesis technique is performed to edit an image using the computed plurality of patches having the different shapes.
    Type: Application
    Filed: February 20, 2014
    Publication date: August 20, 2015
    Inventors: Elya Shechtman, Daniel R. Goldman, Aliakbar Darabi, Nima Khademi Kalantari
  • Publication number: 20140376807
    Abstract: Methods, apparatus, and computer-readable storage media for patch-based image synthesis using color and color gradient voting. A patch matching technique provides an extended patch search space that encompasses geometric and photometric transformations, as well as color and color gradient domain features. The photometric transformations may include gain and bias. The patch-based image synthesis techniques may also integrate image color and color gradients into the patch representation and replace conventional color averaging with a technique that performs voting for colors and color gradients and then solves a screened Poisson equation based on values for colors and color gradients when blending patch(es) with a target image.
    Type: Application
    Filed: September 5, 2014
    Publication date: December 25, 2014
    Inventors: Elya Shechtman, Daniel R. Goldman, Aliakbar Darabi
  • Patent number: 8861868
    Abstract: Methods, apparatus, and computer-readable storage media for patch-based image synthesis. A patch matching technique provides an extended patch search space that encompasses geometric and photometric transformations, as well as gradient domain features. The geometric transformations may include translation, rotation, reflection, scale, and non-uniform scale. The photometric transformations may include gain and bias. Patch-based image synthesis techniques may leverage the extended patch search space in various image synthesis applications. The patch-based image synthesis techniques may also integrate image gradients into the patch representation and replace conventional color averaging with a technique that performs voting for colors and gradients and then solves a screened Poisson equation based on values for colors and gradients when blending patch(es) with a target image.
    Type: Grant
    Filed: August 2, 2012
    Date of Patent: October 14, 2014
    Assignee: Adobe-Systems Incorporated
    Inventors: Elya Shechtman, Daniel R. Goldman, Aliakbar Darabi
  • Patent number: 8712180
    Abstract: The invention produces a higher quality image from a rendering system based on a relationship between the output of a rendering system and the parameters used to compute them. Specifically, noise is removed in rendering by estimating the functional dependency between sample features and the random inputs to the system. Mutual information is applied to a local neighborhood of samples in each part of the image. This dependency is then used to reduce the importance of certain scene features in a cross-bilateral filter, which preserves scene detail. The results produced by the invention are computed in a few minutes thereby making it reasonably robust for use in production environments.
    Type: Grant
    Filed: January 17, 2012
    Date of Patent: April 29, 2014
    Assignee: STC.UNM
    Inventors: Pradeep Sen, Aliakbar Darabi
  • Patent number: 8666180
    Abstract: Compressed sensing can be mapped to a more general set of problems in computer graphics and computer imaging. Representation of a rendered scene in the formulation y=A{circumflex over (x)} produces higher-quality rendering with less samples than previous approaches. A filter formulation ? makes point samples compatible with wavelet and therefore allows reconstruction of 2-D images from a set of measured pixels (point samples).
    Type: Grant
    Filed: December 3, 2010
    Date of Patent: March 4, 2014
    Assignee: STC.UNM
    Inventors: Pradeep Sen, Aliakbar Darabi
  • Publication number: 20140029849
    Abstract: The invention produces a higher quality image from a rendering system based on a relationship between the output of a rendering system and the parameters used to compute them. Specifically, noise is removed in rendering by estimating the functional dependency between sample features and the random inputs to the system. Mutual information is applied to a local neighborhood of samples in each part of the image. This dependency is then used to reduce the importance of certain scene features in a cross-bilateral filter, which preserves scene detail. The results produced by the invention are computed in a few minutes thereby making it reasonably robust for use in production environments.
    Type: Application
    Filed: January 17, 2012
    Publication date: January 30, 2014
    Applicant: STC.UNM
    Inventors: Pradeep Sen, Aliakbar Darabi
  • Publication number: 20130051685
    Abstract: Methods, apparatus, and computer-readable storage media for patch-based image synthesis. A patch matching technique provides an extended patch search space that encompasses geometric and photometric transformations, as well as gradient domain features. The geometric transformations may include translation, rotation, reflection, scale, and non-uniform scale. The photometric transformations may include gain and bias. Patch-based image synthesis techniques may leverage the extended patch search space in various image synthesis applications. The patch-based image synthesis techniques may also integrate image gradients into the patch representation and replace conventional color averaging with a technique that performs voting for colors and gradients and then solves a screened Poisson equation based on values for colors and gradients when blending patch(es) with a target image.
    Type: Application
    Filed: August 2, 2012
    Publication date: February 28, 2013
    Inventors: Elya Shechtman, Daniel R. Goldman, Aliakbar Darabi
  • Publication number: 20120294543
    Abstract: Compressed sensing can be mapped to a more general set of problems in computer graphics and computer imaging. Representation of a rendered scene in the formulation y=A?x produces higher-quality rendering with less samples than previous approaches. A filter formulation ? makes point samples compatible with wavelet and therefore allows reconstruction of 2-D images from a set of measured pixels (point samples).
    Type: Application
    Filed: December 3, 2010
    Publication date: November 22, 2012
    Inventors: Pradeep Sen, Aliakbar Darabi