Patents by Inventor Cristian SMINCHISESCU

Cristian SMINCHISESCU 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: 12249030
    Abstract: The present disclosure provides a statistical, articulated 3D human shape modeling pipeline within a fully trainable, modular, deep learning framework. In particular, aspects of the present disclosure are directed to a machine-learned 3D human shape model with at least facial and body shape components that are jointly trained end-to-end on a set of training data. Joint training of the model components (e.g., including both facial, hands, and rest of body components) enables improved consistency of synthesis between the generated face and body shapes.
    Type: Grant
    Filed: April 30, 2020
    Date of Patent: March 11, 2025
    Assignee: GOOGLE LLC
    Inventors: Cristian Sminchisescu, Hongyi Xu, Eduard Gabriel Bazavan, Andrei Zanfir, William T. Freeman, Rahul Sukthankar
  • Publication number: 20240161470
    Abstract: Systems and methods of the present disclosure are directed to a computer-implemented method for training a machine-learned model for implicit representation of an object. The method can include obtaining a latent code descriptive of a shape of an object comprising one or more object segments. The method can include determining spatial query points. The method can include processing the latent code and spatial query points with segment representation portions of a machine-learned implicit object representation model to obtain implicit segment representations for the object segments. The method can include determining an implicit object representation of the object and semantic data. The method can include evaluating a loss function. The method can include adjusting parameters of the machine-learned implicit object representation model based at least in part on the loss function.
    Type: Application
    Filed: April 21, 2021
    Publication date: May 16, 2024
    Inventors: Cristian Sminchisescu, Thiemo Andreas Alldieck, Hongyi Xu
  • Patent number: 11908071
    Abstract: The present disclosure is generally directed to reconstructing representations of bodies from images. An example method of the present disclosure includes inputting, into a machine-learned reconstruction model, input data descriptive of an image depicting a body; predicting, using a machine-learned marker prediction component of the reconstruction model, a set of surface marker locations on the body; and outputting, using a machine-learned marker poser component of the reconstruction model, an output representation of the body that corresponds to the set of surface marker locations. In the example method, one or more parameters of the reconstruction model were learned at least in part based on a consistency loss corresponding to a distance between relaxed-constraint representations generated from a prior set of surface marker locations predicted according to the one or more parameters and parametric representations generated from the prior set using kinematic constraints associated with the body.
    Type: Grant
    Filed: October 7, 2021
    Date of Patent: February 20, 2024
    Assignee: GOOGLE LLC
    Inventors: Cristian Sminchisescu, Mihai Zanfir, Andrei Zanfir, Eduard Gabriel Bazavan, William Tafel Freeman, Rahul Sukthankar
  • Patent number: 11836221
    Abstract: Systems and methods are directed to a method for estimation of an object state from image data. The method can include obtaining two-dimensional image data depicting an object. The method can include processing, with an estimation portion of a machine-learned object state estimation model, the two-dimensional image data to obtain an initial estimated state of the object. The method can include, for each of one or more refinement iterations, obtaining a previous loss value associated with a previous estimated state for the object, processing the previous loss value to obtain a current estimated state of the object, and evaluating a loss function to determine a loss value associated with the current estimated state of the object. The method can include providing a final estimated state for the object.
    Type: Grant
    Filed: March 12, 2021
    Date of Patent: December 5, 2023
    Assignee: GOOGLE LLC
    Inventors: Cristian Sminchisescu, Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Zanfir, William Tafel Freeman, Rahul Sukthankar
  • Publication number: 20230169727
    Abstract: The present disclosure provides a statistical, articulated 3D human shape modeling pipeline within a fully trainable, modular, deep learning framework. In particular, aspects of the present disclosure are directed to a machine-learned 3D human shape model with at least facial and body shape components that are jointly trained end-to-end on a set of training data. Joint training of the model components (e.g., including both facial, hands, and rest of body components) enables improved consistency of synthesis between the generated face and body shapes.
    Type: Application
    Filed: April 30, 2020
    Publication date: June 1, 2023
    Inventors: Cristian Sminchisescu, Hongyi Xu, Eduard Gabriel Bazavan, Andrei Zanfir, William T. Freeman, Rahul Sukthankar
  • Publication number: 20230116884
    Abstract: The present disclosure is generally directed to reconstructing representations of bodies from images. An example method of the present disclosure includes inputting, into a machine-learned reconstruction model, input data descriptive of an image depicting a body; predicting, using a machine-learned marker prediction component of the reconstruction model, a set of surface marker locations on the body; and outputting, using a machine-learned marker poser component of the reconstruction model, an output representation of the body that corresponds to the set of surface marker locations. In the example method, one or more parameters of the reconstruction model were learned at least in part based on a consistency loss corresponding to a distance between relaxed-constraint representations generated from a prior set of surface marker locations predicted according to the one or more parameters and parametric representations generated from the prior set using kinematic constraints associated with the body.
    Type: Application
    Filed: October 7, 2021
    Publication date: April 13, 2023
    Inventors: Cristian Sminchisescu, Mihai Zanfir, Andrei Zanfir, Eduard Gabriel Bazavan, William Tafel Freeman, Rahul Sukthankar
  • Publication number: 20220292314
    Abstract: Systems and methods are directed to a method for estimation of an object state from image data. The method can include obtaining two-dimensional image data depicting an object. The method can include processing, with an estimation portion of a machine-learned object state estimation model, the two-dimensional image data to obtain an initial estimated state of the object. The method can include, for each of one or more refinement iterations, obtaining a previous loss value associated with a previous estimated state for the object, processing the previous loss value to obtain a current estimated state of the object, and evaluating a loss function to determine a loss value associated with the current estimated state of the object. The method can include providing a final estimated state for the object.
    Type: Application
    Filed: March 12, 2021
    Publication date: September 15, 2022
    Inventors: Cristian Sminchisescu, Andrei Zanfir, Eduard Gabriel Bazavan, Mihai Zanfir, William Tafel Freeman, Rahul Sukthankar
  • Patent number: 11069150
    Abstract: The present invention is directed to generating an image based on first image data of a first person having first pose, first body shape, and first clothing and second image data of a second person having second pose, a second body shape, and second clothing. The generated image represents a transfer of appearance (e.g., clothing) of the second person to the first person. This is achieved by modeling 3d human pose and body shape for each of the persons via triangle mesh, fitting the 3d human pose and body shape models to the images of the persons, transferring appearance using barycentric methods for commonly visible vertices, and learning to color the remaining ones using deep image synthesis techniques.
    Type: Grant
    Filed: June 5, 2019
    Date of Patent: July 20, 2021
    Inventors: Cristian Sminchisescu, Mihai Zanfir, Alin-lonut Popa, Andrei Zanfir, Elisabeta Marinoiu
  • Publication number: 20190371080
    Abstract: The present invention is directed to generating an image based on first image data of a first person having first pose, first body shape, and first clothing and second image data of a second person having second pose, a second body shape, and second clothing. The generated image represents a transfer of appearance (e.g., clothing) of the second person to the first person. This is achieved by modeling 3d human pose and body shape for each of the persons via triangle mesh, fitting the 3d human pose and body shape models to the images of the persons, transferring appearance using barycentric methods for commonly visible vertices, and learning to color the remaining ones using deep image synthesis techniques.
    Type: Application
    Filed: June 5, 2019
    Publication date: December 5, 2019
    Inventors: Cristian Sminchisescu, Mihai Zanfir, Alin-lonut Popa, Andrei Zanfir, Elisabeta Marinoiu
  • Publication number: 20150104102
    Abstract: Feature extraction, coding and pooling, are important components on many contemporary object recognition paradigms. This method explores pooling techniques that encode the second-order statistics of local descriptors inside a region. To achieve this effect, it introduces multiplicative second-order analogues of average and max pooling that together with appropriate non-linearities that lead to exceptional performance on free-form region recognition, without any type of feature coding. Instead of coding, it was found that enriching local descriptors with additional image information leads to large performance gains, especially in conjunction with the proposed pooling methodology. Thus, second-order pooling over free-form regions produces results superior to those of the winning systems in the Pascal VOC 2011 semantic segmentation challenge, with models that are 20,000 times faster.
    Type: Application
    Filed: October 11, 2013
    Publication date: April 16, 2015
    Applicant: Universidade de Coimbra
    Inventors: Joao CARREIRA, Rui CASEIRO, Jorge BATISTA, Cristian SMINCHISESCU