Patents by Inventor Giulio Marin

Giulio Marin 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: 20210243369
    Abstract: A method for calibrating a camera group includes: controlling a first and second cameras to capture first and second images of a first scene, the first camera having a first field of view (FOV), the second camera having a second FOV overlapping the first FOV in a first overlap region; the first scene including a calibration target in the first overlap region; computing a first relative pose based on the first and second images; controlling the second camera and a third camera to capture third and fourth images of a second scene, the third camera having a third FOV overlapping the second FOV in a second overlap region, the second scene including a calibration target in the second overlap region; computing a second relative pose based on the third and fourth images; and computing a third relative pose based on the first and second relative poses.
    Type: Application
    Filed: September 11, 2020
    Publication date: August 5, 2021
    Inventors: Carlo Dal Mutto, Giulio Marin
  • Patent number: 10805535
    Abstract: A method for calibrating a camera group includes: controlling a first and second cameras to capture first and second images of a first scene, the first camera having a first field of view (FOV), the second camera having a second FOV overlapping the first FOV in a first overlap region; the first scene including a calibration target in the first overlap region; computing a first relative pose based on the first and second images; controlling the second camera and a third camera to capture third and fourth images of a second scene, the third camera having a third FOV overlapping the second FOV in a second overlap region, the second scene including a calibration target in the second overlap region; computing a second relative pose based on the third and fourth images; and computing a third relative pose based on the first and second relative poses.
    Type: Grant
    Filed: May 24, 2019
    Date of Patent: October 13, 2020
    Assignee: AQUIFI, INC.
    Inventors: Carlo Dal Mutto, Giulio Marin
  • Publication number: 20190364206
    Abstract: A method for calibrating a camera group includes: controlling a first and second cameras to capture first and second images of a first scene, the first camera having a first field of view (FOV), the second camera having a second FOV overlapping the first FOV in a first overlap region; the first scene including a calibration target in the first overlap region; computing a first relative pose based on the first and second images; controlling the second camera and a third camera to capture third and fourth images of a second scene, the third camera having a third FOV overlapping the second FOV in a second overlap region, the second scene including a calibration target in the second overlap region; computing a second relative pose based on the third and fourth images; and computing a third relative pose based on the first and second relative poses.
    Type: Application
    Filed: May 24, 2019
    Publication date: November 28, 2019
    Inventors: Carlo Dal Mutto, Giulio Marin
  • Patent number: 10453185
    Abstract: A method for capturing a depth map includes: controlling a plurality of cameras to capture, concurrently, a plurality of first images during a first exposure interval, each of the cameras concurrently capturing a corresponding one of the first images, the cameras having overlapping fields of view; controlling a projection source to emit light at a first illumination level during the first exposure interval; controlling the cameras to capture, concurrently, a plurality of second images during a second exposure interval, each of the cameras concurrently capturing a corresponding one of the second images; controlling the projection source to emit light at a second illumination level during the second exposure interval, the second illumination level being different from the first illumination level; combining the first images with the second images to generate a depth map; and outputting the depth map.
    Type: Grant
    Filed: November 2, 2016
    Date of Patent: October 22, 2019
    Assignee: AQUIFI, INC.
    Inventors: Carlo Dal Mutto, Abbas Rafii, Pietro Salvagnini, Aryan Hazeghi, Michele Stoppa, Francesco Peruch, Giulio Marin
  • Publication number: 20190005711
    Abstract: A method for generating a three-dimensional (3D) model of an object includes: capturing images of the object from a plurality of viewpoints, the images including color images; generating a 3D model of the object from the images, the 3D model including a plurality of planar patches; for each patch of the planar patches: mapping image regions of the images to the patch, each image region including at least one color vector; and computing, for each patch, at least one minimal color vector among the color vectors of the image regions mapped to the patch; generating a diffuse component of a bidirectional reflectance distribution function (BRDF) for each patch of planar patches of the 3D model in accordance with the at least one minimal color vector computed for each patch; and outputting the 3D model with the BRDF for each patch.
    Type: Application
    Filed: August 20, 2018
    Publication date: January 3, 2019
    Inventors: Giulio Marin, Abbas Rafii, Carlo Dal Mutto, Kinh Tieu, Giridhar Murali, Alvise Memo
  • Publication number: 20180322623
    Abstract: A method for detecting defects in objects includes: controlling, by a processor, one or more depth cameras to capture a plurality of depth images of a target object; computing, by the processor, a three-dimensional (3-D) model of the target object using the depth images; rendering, by the processor, one or more views of the 3-D model; computing, by the processor, a descriptor by supplying the one or more views of the 3-D model to a convolutional stage of a convolutional neural network; supplying, by the processor, the descriptor to a defect detector to compute one or more defect classifications of the target object; and outputting the one or more defect classifications of the target object.
    Type: Application
    Filed: May 8, 2018
    Publication date: November 8, 2018
    Inventors: Alvise Memo, David Demirdjian, Giulio Marin, Kinh Tieu, Francesco Peruch, Pietro Salvagnini, Giridhar Murali, Carlo Dal Mutto, Guido Cesare
  • Patent number: 10055882
    Abstract: A method for generating a three-dimensional (3D) model of an object includes: capturing images of the object from a plurality of viewpoints, the images including color images; generating a 3D model of the object from the images, the 3D model including a plurality of planar patches; for each patch of the planar patches: mapping image regions of the images to the patch, each image region including at least one color vector; and computing, for each patch, at least one minimal color vector among the color vectors of the image regions mapped to the patch; generating a diffuse component of a bidirectional reflectance distribution function (BRDF) for each patch of planar patches of the 3D model in accordance with the at least one minimal color vector computed for each patch; and outputting the 3D model with the BRDF for each patch.
    Type: Grant
    Filed: August 15, 2017
    Date of Patent: August 21, 2018
    Assignee: Aquifi, Inc.
    Inventors: Giulio Marin, Abbas Rafii, Carlo Dal Mutto, Kinh Tieu, Giridhar Murali, Alvise Memo
  • Patent number: 9912862
    Abstract: A three-dimensional scanning system includes: a camera configured to capture images; a processor; and memory coupled to the camera and the processor, the memory being configured to store: the images captured by the camera; and instructions that, when executed by the processor, cause the processor to: control the camera to capture one or more initial images of a subject from a first pose of the camera; compute a guidance map in accordance with the one or more initial images to identify one or more next poses; control the camera to capture one or more additional images from at least one of the one or more next poses; update the guidance map in accordance with the one or more additional images; and output the images captured by the camera to generate a three-dimensional model.
    Type: Grant
    Filed: February 28, 2017
    Date of Patent: March 6, 2018
    Assignee: Aquifi, Inc.
    Inventors: Francesco Peruch, Giridhar Murali, Giulio Marin, Abbas Rafii, Kinh Tieu
  • Publication number: 20180047208
    Abstract: A method for generating a three-dimensional (3D) model of an object includes: capturing images of the object from a plurality of viewpoints, the images including color images; generating a 3D model of the object from the images, the 3D model including a plurality of planar patches; for each patch of the planar patches: mapping image regions of the images to the patch, each image region including at least one color vector; and computing, for each patch, at least one minimal color vector among the color vectors of the image regions mapped to the patch; generating a diffuse component of a bidirectional reflectance distribution function (BRDF) for each patch of planar patches of the 3D model in accordance with the at least one minimal color vector computed for each patch; and outputting the 3D model with the BRDF for each patch.
    Type: Application
    Filed: August 15, 2017
    Publication date: February 15, 2018
    Inventors: Giulio Marin, Abbas Rafii, Carlo Dal Mutto
  • Patent number: 9826216
    Abstract: A pattern projection system includes a coherent light source, a repositionable DOE disposed to receive coherent light from said coherent light source and disposed to output at least one pattern of projectable light onto a scene to be imaged by an (x,y) two-dimensional optical acquisition system. Coherent light speckle artifacts in the projected pattern are reduced by rapidly controllably repositioning the DOE or the entire pattern projection system. Different projectable patterns are selected from a set of M patterns that are related to each other by a translation and/or rotation operation in two-dimensional cosine space. A resultant (x,y,z) depth map has improved quality and robustness due to projection of the selected patterns. Three-dimensional (x,y,z) depth data obtained from two-dimensional imaged data including despeckling is higher quality data than if projected patterns without despeckling were used.
    Type: Grant
    Filed: September 23, 2016
    Date of Patent: November 21, 2017
    Assignee: AQUIFI, INC.
    Inventors: Aryan Hazeghi, Carlo Dal Mutto, Giulio Marin, Francesco Peruch, Michele Stoppa, Abbas Rafii
  • Publication number: 20170251143
    Abstract: A three-dimensional scanning system includes: a camera configured to capture images; a processor; and memory coupled to the camera and the processor, the memory being configured to store: the images captured by the camera; and instructions that, when executed by the processor, cause the processor to: control the camera to capture one or more initial images of a subject from a first pose of the camera; compute a guidance map in accordance with the one or more initial images to identify one or more next poses; control the camera to capture one or more additional images from at least one of the one or more next poses; update the guidance map in accordance with the one or more additional images; and output the images captured by the camera to generate a three-dimensional model.
    Type: Application
    Filed: February 28, 2017
    Publication date: August 31, 2017
    Inventors: Francesco Peruch, Giridhar Murali, Giulio Marin, Abbas Rafii, Kinh Tieu
  • Publication number: 20170142312
    Abstract: A method for capturing a depth map includes: controlling a plurality of cameras to capture, concurrently, a plurality of first images during a first exposure interval, each of the cameras concurrently capturing a corresponding one of the first images, the cameras having overlapping fields of view; controlling a projection source to emit light at a first illumination level during the first exposure interval; controlling the cameras to capture, concurrently, a plurality of second images during a second exposure interval, each of the cameras concurrently capturing a corresponding one of the second images; controlling the projection source to emit light at a second illumination level during the second exposure interval, the second illumination level being different from the first illumination level; combining the first images with the second images to generate a depth map; and outputting the depth map.
    Type: Application
    Filed: November 2, 2016
    Publication date: May 18, 2017
    Inventors: Carlo Dal Mutto, Abbas Rafii, Pietro Salvagnini, Aryan Hazeghi, Michele Stoppa, Francesco Peruch, Giulio Marin
  • Patent number: 9507417
    Abstract: Embodiments in accordance with this invention disclose systems and methods for implementing head tracking based graphical user interfaces that incorporate gesture reactive interface objects. The disclosed embodiments perform a method in which a GUI includes interface objects is rendered and displayed. Image data of an interaction zone is captured. A targeting gestured targeting a targeted interface object is detected in the captured image data and a set of 3D head interaction gestures are enabled. Additional image data is captured. Motion of at least a portion of a human head is detected and one of the 3D head interactions is identified. The rendering of the interface is modified in response to the detection of one of the 3D head interactions and the modified interface is displayed.
    Type: Grant
    Filed: January 7, 2015
    Date of Patent: November 29, 2016
    Assignee: Aquifi, Inc.
    Inventors: Carlo Dal Mutto, Giulio Marin, Abbas Rafii, Tony Zuccarino
  • Patent number: 9503708
    Abstract: A projection system configured to emit patterned light along a projection optical axis includes: a diffractive optical element configured to perform a collimation function on the light emitted by the light emitter and to perform a pattern generation function to replicate the collimated light in a pattern, the pattern having substantially no collimated zero-order; and a light emitter configured to emit light toward the diffractive optical element, wherein the collimation function is configured to collimate the light emitted from the light emitter, and wherein the pattern generation function is configured to replicate the collimated light to produce the patterned light.
    Type: Grant
    Filed: June 18, 2015
    Date of Patent: November 22, 2016
    Assignee: Aquifi, Inc.
    Inventors: Aryan Hazeghi, Giulio Marin, Francesco Peruch, Carlo Dal Mutto, Abbas Rafii
  • Publication number: 20160127714
    Abstract: A projection system configured to emit patterned light along a projection optical axis includes: a diffractive optical element configured to perform a collimation function on the light emitted by the light emitter and to perform a pattern generation function to replicate the collimated light in a pattern, the pattern having substantially no collimated zero-order; and a light emitter configured to emit light toward the diffractive optical element, wherein the collimation function is configured to collimate the light emitted from the light emitter, and wherein the pattern generation function is configured to replicate the collimated light to produce the patterned light.
    Type: Application
    Filed: June 18, 2015
    Publication date: May 5, 2016
    Inventors: Aryan Hazeghi, Giulio Marin, Francesco Peruch, Carlo Dal Mutto, Abbas Rafii
  • Publication number: 20150192991
    Abstract: Embodiments in accordance with this invention disclose systems and methods for implementing head tracking based graphical user interfaces that incorporate gesture reactive interface objects. The disclosed embodiments perform a method in which a GUI includes interface objects is rendered and displayed. Image data of an interaction zone is captured. A targeting gestured targeting a targeted interface object is detected in the captured image data and a set of 3D head interaction gestures are enabled. Additional image data is captured. Motion of at least a portion of a human head is detected and one of the 3D head interactions is identified. The rendering of the interface is modified in response to the detection of one of the 3D head interactions and the modified interface is displayed.
    Type: Application
    Filed: January 7, 2015
    Publication date: July 9, 2015
    Inventors: Carlo Dal Mutto, Giulio Marin, Abbas Rafii, Tony Zuccarino