Patents by Inventor Umar Iqbal

Umar Iqbal 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).

  • Patent number: 11488418
    Abstract: Estimating a three-dimensional (3D) pose of an object, such as a hand or body (human, animal, robot, etc.), from a 2D image is necessary for human-computer interaction. A hand pose can be represented by a set of points in 3D space, called keypoints. Two coordinates (x,y) represent spatial displacement and a third coordinate represents a depth of every point with respect to the camera. A monocular camera is used to capture an image of the 3D pose, but does not capture depth information. A neural network architecture is configured to generate a depth value for each keypoint in the captured image, even when portions of the pose are occluded, or the orientation of the object is ambiguous. Generation of the depth values enables estimation of the 3D pose of the object.
    Type: Grant
    Filed: December 28, 2020
    Date of Patent: November 1, 2022
    Assignee: NVIDIA Corporation
    Inventors: Umar Iqbal, Pavlo Molchanov, Thomas Michael Breuel, Jan Kautz
  • Patent number: 11417011
    Abstract: Learning to estimate a 3D body pose, and likewise the pose of any type of object, from a single 2D image is of great interest for many practical graphics applications and generally relies on neural networks that have been trained with sample data which annotates (labels) each sample 2D image with a known 3D pose. Requiring this labeled training data however has various drawbacks, including for example that traditionally used training data sets lack diversity and therefore limit the extent to which neural networks are able to estimate 3D pose. Expanding these training data sets is also difficult since it requires manually provided annotations for 2D images, which is time consuming and prone to errors. The present disclosure overcomes these and other limitations of existing techniques by providing a model that is trained from unlabeled multi-view data for use in 3D pose estimation.
    Type: Grant
    Filed: June 9, 2020
    Date of Patent: August 16, 2022
    Assignee: NVIDIA CORPORATION
    Inventors: Umar Iqbal, Pavlo Molchanov, Jan Kautz
  • Publication number: 20220222832
    Abstract: A method and system are provided for tracking instances within a sequence of video frames. The method includes the steps of processing an image frame by a backbone network to generate a set of feature maps, processing the set of feature maps by one or more prediction heads, and analyzing the embedding features corresponding to a set of instances in two or more image frames of the sequence of video frames to establish a one-to-one correlation between instances in different image frames. The one or more prediction heads includes an embedding head configured to generate a set of embedding features corresponding to one or more instances of an object identified in the image frame. The method may also include training the one or more prediction heads using a set of annotated image frames and/or a plurality of sequences of unlabeled video frames.
    Type: Application
    Filed: January 6, 2022
    Publication date: July 14, 2022
    Inventors: Yang Fu, Sifei Liu, Umar Iqbal, Shalini De Mello, Jan Kautz
  • Patent number: 11361507
    Abstract: Estimating a three-dimensional (3D) pose and shape of an articulated body mesh is useful for many different applications including health and fitness, entertainment, and computer graphics. A set of estimated 3D keypoint positions for a human body structure are processed to compute parameters defining the pose and shape of a parametric human body mesh using a set of geometric operations. During processing, 3D keypoints are extracted from the parametric human body mesh and a set of rotations are computed to align the extracted 3D keypoints with the estimated 3D keypoints. The set of rotations may correctly position a particular 3D keypoint location at a “joint”, but an arbitrary number of rotations of the “joint” keypoint may produce a twist in a connection to a child keypoint. Rules are applied to the set of rotations to resolve ambiguous twists and articulate the parametric human body mesh according to the computed parameters.
    Type: Grant
    Filed: May 7, 2021
    Date of Patent: June 14, 2022
    Assignee: NVIDIA Corporation
    Inventors: Umar Iqbal, Pavlo Molchanov, Jan Kautz, Yun Rong Guo, Cheng Xie
  • Publication number: 20210248772
    Abstract: Learning to estimate a 3D body pose, and likewise the pose of any type of object, from a single 2D image is of great interest for many practical graphics applications and generally relies on neural networks that have been trained with sample data which annotates (labels) each sample 2D image with a known 3D pose. Requiring this labeled training data however has various drawbacks, including for example that traditionally used training data sets lack diversity and therefore limit the extent to which neural networks are able to estimate 3D pose. Expanding these training data sets is also difficult since it requires manually provided annotations for 2D images, which is time consuming and prone to errors. The present disclosure overcomes these and other limitations of existing techniques by providing a model that is trained from unlabeled multi-view data for use in 3D pose estimation.
    Type: Application
    Filed: June 9, 2020
    Publication date: August 12, 2021
    Inventors: Umar Iqbal, Pavlo Molchanov, Jan Kautz
  • Publication number: 20210233273
    Abstract: Apparatuses, systems, and techniques that determine the pose of a human hand from a 2-D image are described herein. In at least one embodiment, training of a neural network is augmented using weakly labeled or unlabeled pose data which is augmented with losses based on a human hand model.
    Type: Application
    Filed: January 24, 2020
    Publication date: July 29, 2021
    Inventors: Adrian Spurr, Pavlo Molchanov, Umar Iqbal, Jan Kautz
  • Publication number: 20210150757
    Abstract: Apparatuses, systems, and techniques to identify orientations of objects within images. In at least one embodiment, one or more neural networks are trained to identify an orientations of one or more objects based, at least in part, on one or more characteristics of the object other than the object's orientation.
    Type: Application
    Filed: November 20, 2019
    Publication date: May 20, 2021
    Inventors: Siva Karthik Mustikovela, Varun Jampani, Shalini De Mello, Sifei Liu, Umar Iqbal, Jan Kautz
  • Publication number: 20210117661
    Abstract: Estimating a three-dimensional (3D) pose of an object, such as a hand or body (human, animal, robot, etc.), from a 2D image is necessary for human-computer interaction. A hand pose can be represented by a set of points in 3D space, called keypoints. Two coordinates (x,y) represent spatial displacement and a third coordinate represents a depth of every point with respect to the camera. A monocular camera is used to capture an image of the 3D pose, but does not capture depth information. A neural network architecture is configured to generate a depth value for each keypoint in the captured image, even when portions of the pose are occluded, or the orientation of the object is ambiguous. Generation of the depth values enables estimation of the 3D pose of the object.
    Type: Application
    Filed: December 28, 2020
    Publication date: April 22, 2021
    Inventors: Umar Iqbal, Pavlo Molchanov, Thomas Michael Breuel, Jan Kautz
  • Patent number: 10929654
    Abstract: Estimating a three-dimensional (3D) pose of an object, such as a hand or body (human, animal, robot, etc.), from a 2D image is necessary for human-computer interaction. A hand pose can be represented by a set of points in 3D space, called keypoints. Two coordinates (x,y) represent spatial displacement and a third coordinate represents a depth of every point with respect to the camera. A monocular camera is used to capture an image of the 3D pose, but does not capture depth information. A neural network architecture is configured to generate a depth value for each keypoint in the captured image, even when portions of the pose are occluded, or the orientation of the object is ambiguous. Generation of the depth values enables estimation of the 3D pose of the object.
    Type: Grant
    Filed: March 1, 2019
    Date of Patent: February 23, 2021
    Assignee: NVIDIA Corporation
    Inventors: Umar Iqbal, Pavlo Molchanov, Thomas Michael Breuel, Jan Kautz
  • Publication number: 20200334543
    Abstract: A neural network is trained to identify one or more features of an image. The neural network is trained using a small number of original images, from which a plurality of additional images are derived. The additional images generated by rotating and decoding embeddings of the image in a latent space generated by an autoencoder. The images generated by the rotation and decoding exhibit changes to a feature that is in proportion to the amount of rotation.
    Type: Application
    Filed: April 19, 2019
    Publication date: October 22, 2020
    Inventors: Seonwook Park, Shalini De Mello, Pavlo Molchanov, Umar Iqbal, Jan Kautz
  • Publication number: 20190278983
    Abstract: Estimating a three-dimensional (3D) pose of an object, such as a hand or body (human, animal, robot, etc.), from a 2D image is necessary for human-computer interaction. A hand pose can be represented by a set of points in 3D space, called keypoints. Two coordinates (x,y) represent spatial displacement and a third coordinate represents a depth of every point with respect to the camera. A monocular camera is used to capture an image of the 3D pose, but does not capture depth information. A neural network architecture is configured to generate a depth value for each keypoint in the captured image, even when portions of the pose are occluded, or the orientation of the object is ambiguous. Generation of the depth values enables estimation of the 3D pose of the object.
    Type: Application
    Filed: March 1, 2019
    Publication date: September 12, 2019
    Inventors: Umar Iqbal, Pavlo Molchanov, Thomas Michael Breuel, Jan Kautz
  • Publication number: 20110274617
    Abstract: A nanoconjugate is formed from a self-assembled unilamellar vesicle (ULV), at least one contrast agent which may be a MRI contrast agent, a radioisotope or a fluorophore, and at least one antibody, which may be an IgG or an antibody fragment such as a single-domain antibody. The nanoconjugate be targetted with the antibody to receptors specific to certain disease states, and thus be used in diagnostic and imaging methods using the properties o contrast agent.
    Type: Application
    Filed: November 26, 2009
    Publication date: November 10, 2011
    Applicant: NATIONAL RESEARCH COUNCIL OF CANADA
    Inventors: Abedelnasser Abulrob, Danica Stanimirovic, Umar Iqbal, Mu-Ping Nieh, John Katsaras