Verizon Patent and Licensing Inc.

Spinella IP Holdings, Inc.

A2zlogix, Inc.

Vidhya Seran

William L Gaddy

Elena Dotsenko

Denny Breitenfeld

Liang Luo

Nazneen Khan

Yong Liu

Tom Hsi Hao Shang

Richard John Kern, Ii

Oliver S Castaneda

Dan Sun

Timothy Atchley

Igor Gomon

Leonardo Taccari

Francesco Sambo

Leonardo Sarti

Douglas Coimbra De Andrade

Tommaso Bianconcini

Aurel Pjetri

Jerry Gamble, Jr

Vincent James Spinella

Nikhil Sadashiv Pantpratinidhi

Eric Norman Azares

Stephen Cole

John Galluzzo

Syed B Aziz

Chidambaram Ramanathan

Stephen Nowalk

Robert Strelec

Jeremy E Hampsten

Kevin M Byrd

Duane Burton Molitor

Stephen Andrew Norwalk

Lonnie Souder

An illustrative point cloud segmentation system generates an instance-wise semantic mask for a particular source image of a set of source images that has been used to construct a 3D point cloud representing a scene that includes one or more objects. The point cloud segmentation system maps a set of 3D points from the 3D point cloud to corresponding 2D points of the particular source image, then labels, based on contours defined by the instance-wise semantic mask to demarcate the one or more objects, the mapped set of 3D points in accordance with where the corresponding 2D point for each mapped 3D point is positioned with respect to the contours. Based on the labeling of the mapped 3D points, the point cloud segmentation system produces a segmented 3D point cloud including an instance-wise segmentation of the one or more objects at the scene. Corresponding methods and systems are also disclosed.

Methods and systems for instance-wise segmentation of a 3D point cloud based on segmented 2D images

An illustrative camera calibration system accesses a set of images captured by one or more cameras at a scene. The set of images may each depict a same element of image content present at the scene, but may depict the element of image content differently in each image so as to show an apparent movement of the element from one image to another. The camera calibration system applies a structure-from-motion algorithm to the set of images to generate calibration parameters for the one or more cameras based on the apparent movement of the element of image content shown in the set of images. Additionally, the camera calibration system provides the calibration parameters for the one or more cameras to a 3D modeling system configured to model the scene based on the set of images. Corresponding methods and systems are also disclosed.

Methods and systems for camera calibration based on apparent movement of image content at a scene

A first capture engine application may synchronize a first clock to a global time domain to which a second clock used by a second capture engine application is also synchronized. The first capture engine application may receive a first image frame having a camera timestamp indicating a capture time of the first image frame with respect to a camera time domain. Based on the camera timestamp and the synchronized first clock, the first capture engine application may annotate the first image frame with a global timestamp indicating the capture time of the first image frame with respect to the global time domain. The first capture engine application may then transmit the annotated first image frame at a same transmission time as the second capture engine application also synchronously transmits a second image frame that is also annotated with the global timestamp. Corresponding methods and systems are also disclosed.

Methods and systems for synchronizing image frames captured by a camera array

An illustrative content server system associated with a server domain may transmit, to a client device associated with a client domain, a data stream representing media content. The media content is represented at a first quality level for presentation within a presentation environment as the data stream is transmitted. Based on environment data captured in the client domain to represent real-time conditions of the presentation environment as the media content is presented, the content server system may determine an engagement parameter representing a real-time engagement level of a user with respect to the media content. Based on this engagement parameter, the content server system may adjust, in real time during the transmitting of the data stream and presentation of the media content, the data stream to represent the media content at a second quality level that is different from the first quality level. Corresponding methods and systems are also disclosed.

Bandwidth management methods and systems based on client-side environment data

A device may receive video data and corresponding GPS data and IMU data associated with a vehicle, and may remove video frames from the video data to generate modified video data. The device may select objects and image regions of video frames of the modified video data, and may determine a current speed and a current turn angle of the vehicle based on the GPS data, the IMU data, and the modified video data. The device may mask the objects of the video frames of the modified video data to learn first features, and may mask the image regions of the video frames of the modified video data to learn second features. The device may generate a trained neural network model based on the current speed, the current turn angle, the first features, and the second features, and may implement the trained neural network model in the vehicle.

Systems and methods for training a driving agent based on real-world driving data

An illustrative volumetric content production system may access first capture data and second capture data. These first capture data may represent an entirety of a capture target and may be captured by a fixed camera system including a first plurality of image capture devices having respective fixed viewpoints with respect to the capture target. The second capture data may represent a portion of the capture target less than the entirety of the capture target and may be captured by a dynamic camera system including a second plurality of image capture devices having respective dynamic viewpoints with respect to the capture target. Based on the first and second capture data, the volumetric content production system may generate a volumetric representation of an object included in the portion of the capture target in accordance with principles described herein. Corresponding methods and systems are also disclosed.

Methods and systems for producing volumetric content using combined fixed and dynamic camera systems

An illustrative point cloud compression system accesses an input point cloud dataset representative of a point cloud comprising a plurality of points. The point cloud compression system identifies a first attribute dataset and a second attribute dataset within the input point cloud dataset. Based on an application of a transform algorithm to the first and second attribute datasets, respectively, the point cloud compression system generates 1) a first low-frequency component and a first high-frequency component of the first attribute dataset, and 2) a second low-frequency component and a second high-frequency component of the second attribute dataset. The point cloud compression system then generates an output point cloud dataset that prioritizes both the first and second low-frequency components above both the first and second high-frequency components. Corresponding methods and systems are also disclosed.

Methods and systems for scalable compression of point cloud data

An illustrative 3D modeling system generates a first voxelized representation of an object with respect to a voxel space and a second voxelized representation of the object with respect to the voxel space. Based on a first normal of a first voxel included in the first voxelized representation and a second normal of a second voxel included in the second voxelized representation, the 3D modeling system identifies a mergeable intersection between the first and second voxels. Based on the first and second voxelized representations, the 3D modeling system generates a merged voxelized representation of the object with respect to the voxel space. The merged voxelized representation includes a single merged voxel generated, based on the identified mergeable intersection, to represent both the first and second voxels. Corresponding methods and systems are also disclosed.

Methods and systems for 3D modeling of an object by merging voxelized representations of the object

An illustrative content augmentation system identifies a presentation context dataset indicating how an extended reality (XR) presentation device is to present XR content in connection with a presentation of primary content. Based on the presentation context dataset, the content augmentation system selects a subset of secondary content items from a set of secondary content items each configured for presentation as XR content that augments the presentation of the primary content. The content augmentation system also provides the selected subset of secondary content items for presentation by the XR presentation device in connection with the presentation of the primary content. Corresponding methods and systems are also disclosed.

Methods and systems for customizing augmentation of a presentation of primary content

An illustrative scene capture system determines a set of two-dimensional (2D) feature pairs each representing a respective correspondence between particular features depicted in both a first intensity image from a first vantage point and a second intensity image from a second vantage point. Based on the set of 2D feature pairs, the system determines a set of candidate three-dimensional (3D) feature pairs for a first depth image from the first vantage point and a second depth image from the second vantage point. The system selects a subset of selected 3D feature pairs from the set of candidate 3D feature pairs in a manner configured to minimize an error associated with a transformation between the first depth image and the second depth image. Based on the subset of selected 3D feature pairs, the system manages calibration parameters for surface data capture devices that captured the intensity and depth images.

Methods and systems for calibrating surface data capture devices

An illustrative volumetric processing system generates a plurality of point clouds each representing an object from a different vantage point. Based on the plurality of point clouds, the volumetric processing system consolidates point cloud data corresponding to a surface of the object. Based on the consolidated point cloud data for the object, the volumetric processing system generates a voxel grid representative of the object. Based on the voxel grid, the volumetric processing system generates a set of rendered patches each depicting at least a part of the surface of the object. Corresponding methods and systems are also disclosed.

Systems and methods for processing volumetric data

An exemplary method includes establishing, by a sending device, a communication session with a receiving device, the communication session configured to transfer an array of related, sequenced data blocks from the sending device to the receiving device. The method includes sending one or more parameter messages including parameters associated with the array of data blocks. The method includes receiving one or more parameter acknowledgement messages to the one or more parameter messages, the one or more parameter acknowledgement messages including a plurality of memory addresses of the receiving device, the plurality of memory addresses including a respective memory address for each data block of the array of data blocks. The method includes sending the array of data blocks to the receiving device, each data block of the array of data blocks sent to the respective memory address using a remote direct memory access (RDMA) protocol.

Methods and systems for transmitting arrays of sequenced data blocks

An exemplary image generation system accesses a full atlas frame sequence that incorporates a set of image sequences combined within the full atlas frame sequence as atlas tiles. The system generates a first partial atlas frame sequence that incorporates a first subset of image sequences selected from the set of image sequences incorporated in the full atlas frame sequence, as well as a second partial atlas frame sequence that incorporates a second subset of image sequences selected from the set of image sequences. The second subset includes a different combination of image sequences than the first subset and includes at least one image sequence in common with the first subset. The system provides the first partial atlas frame sequence to a first video encoder and the second partial atlas frame sequence to a second video encoder communicatively coupled with the first video encoder. Corresponding methods and systems are also disclosed.

Methods and systems for using atlas frames to process data representative of a scene

An exemplary volumetric processing system includes a set of point cloud generators, a point cloud organizer, a voxelizer, and a set of patch renderers. The point cloud generators correspond to image capture systems disposed at different vantage points to capture color and depth data for an object located within a capture area. The point cloud generators generate respective point clouds for the different vantage points based on the captured surface data. The point cloud organizer consolidates point cloud data that corresponds to a surface of the object. The voxelizer generates a voxel grid representative of the object based on the consolidated point cloud data. The set of patch renderers generates, based on the voxel grid, a set of rendered patches each depicting at least a part of the surface of the object. Corresponding systems and methods are also disclosed.

Systems and methods for processing volumetric data using a modular network architecture

An exemplary video encoding system accesses an image set that includes first and second consecutive color data images depicting a virtual reality scene from a particular vantage point, and first and second consecutive depth data images corresponding to the color data images. The system performs a first-pass video encoding of the image set by identifying motion vector data associated with a transformation from the first to the second color data image, and abstaining from analyzing a transformation from the first to the second depth data image. The system then performs a second-pass video encoding of the image set based on the identified motion vector data by encoding the first and second color data images into a color video stream to be rendered by a media player device, and the first and second depth data images into a depth video stream to be rendered by the media player device.

Growing community of inventors

Irving, TX, United States of America

Vidhya Seran