Qualcomm Incorporated

Qualcomm Technologies, Inc.

Bojan Vrcelj

Raghuraman Krishnamoorthi

Krishna Kiran Mukkavilli

Ashok Mantravadi

Fuyun Ling

Michael Mao Wang

Rajiv Vijayan

Ajit Venkat Rao

Murali Chari

Serafin Diaz Spindola

Vinay Melkote Krishnaprasad

Thomas Stockhammer

Prashanth Haridas Hande

Gerhard Reitmayr

Linbo Li

Dieter Schmalstieg

Vinay Murthy

Joseph Daniel Garvey

Jing Jiang

Peerapol Tinnakornsrisuphap

Bibhu P Mohanty

Pawan Kumar Baheti

Tao Tian

Bruce Collins

Alok Kumar Gupta

Qi Xue

Mahesh Ramachandran

Seong Taek Chung

Thomas Sun

Sandeep Kanakapura Lakshmikantha

Mina Ayman Saleh Yanni Makar

Maksim Krasnyanskiy

Kishor Kumar Barman

Arjun Sitaram

Mina Makar

Daniel Knoblauch

Young Hoon Lee

Soumyajit Bijankumar Deb

Gary G McGrath

Raghuraman Krishnamoorhi

Surbhit Sinha

Dieter Schmalsteig

Murali Ramaswamy Chari

The present disclosure relates to methods and apparatus for computer processing. Aspects of the present disclosure can determine at least one of a quality, latency, or capacity of a communication link for communication between a client device and a server. Aspects of the present disclosure can also determine a computational load for an application computation between the client device and the server. Moreover, aspects of the present disclosure can adjust a computational distribution for the application computation between the client device and the server based on at least one of the computational load for the application computation or the at least one of the quality, latency, or capacity of the communication link. Aspects of the present disclosure can also determine a computational capacity of at least one of the client device or the server.

Distribution of application computations

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a wireless communication device may predict user behavior in an extended reality (XR) application on a user equipment (UE) based at least in part on current content presented by the XR application. The wireless communication device may predict channel information for a communication link of the UE based at least in part on the predicted user behavior. The wireless communication device may adjust one or more parameters of the communication link based at least in part on the predicted channel information. Numerous other aspects are described.

Adjusting communication link for user behavior in application

A client device of a split rendering graphics processing architecture, receives an encoded shading atlas for a current frame. The encoded shading atlas is characterized by slices. The client decodes the received encoded shading atlas and identifies unsuccessfully decoded slices. The client then determines whether each patch of the decoded shading atlas intersects an identified unsuccessfully decoded slice. The client determines, for each intersecting patch, whether a prior valid version of each intersecting patch is stored at the client device. The client error conceals each intersecting patch having a prior valid version stored at the client device with the corresponding prior valid version to create an error concealed atlas. The client renders the current frame using the error concealed atlas.

Error concealment in split rendering using shading atlases

The present disclosure relates to methods and apparatus for graphics processing. Aspects of the present disclosure may identify a first content group and a second content group in a scene. Further, aspects of the present disclosure may determine whether at least a portion of the first content group occludes or potentially occludes at least a portion of the second content group. Additionally, the present disclosure may represent the first content group and the second content group based on the determination whether at least a portion of the first content group occludes or potentially occludes at least a portion of the second content group. In some aspects, the first content group may include at least some real content and the second content group includes at least some augmented content. The present disclosure may also render at least a portion of surfaces of the first content group using an occlusion material.

Methods and apparatus for handling occlusions in split rendering

Graphics processing in a client device includes receiving, as part of a vector streaming split rendering process, a bit stream encoding a sequence of shading atlases of the process. Each shading atlas includes blocks. The client decodes a particular shading atlas of the sequence of shading atlases, and determines that a particular block of the particular shading atlas was unsuccessfully decoded. The client identifies a stored block of a prior shading atlas of the sequence of shading atlases as a successfully decoded earlier version of the particular block. The client renders the particular shading atlas using the stored block instead of the particular block.

Error concealment in split rendering

A method of dynamically updating a feature database that contains features corresponding to a known target object includes providing an image, extracting a first set of features from within the captured image, and comparing the first set of features to the features stored in the feature database. If it is determined that the target object is present in the image then at least one of the extracted features of the first set that are not already included in the feature database are added to the feature database.

Incremental learning for dynamic feature database management in an object recognition system

Methods and apparatus for distribution of application computations

An improved wireless split rendering system for displaying Extended Reality (XR) content is discussed. A rendering server and client head-mounted device (HMD) may communicate over a wireless medium, where communication control is given to a server application layer logic. This allows the server to use request pose information from the HMD only when needed for rendering, while preserving bandwidth on the wireless medium for transmitting frames of the rendered content. This reduces contention and improves channel efficiency.

Cross layer traffic optimization for split XR

Aspects of the present disclosure provide a method for compressing a point cloud. The method includes determining a sub-division technique for the volume based on one or more numbers derived from a distribution of points in the volume, dividing the volume into a number of sub-volumes according to the sub-division technique, and determining whether each sub-volume of the sub-volumes is occupied by at least one point. The method includes generating a bit sequence for the volume comprising a control code that is based on the sub-division technique and an occupancy indicator that indicates whether or not each sub-volume is occupied by at least one point.

Compression of point clouds via a novel hybrid coder

A method, an apparatus, and a computer-readable medium for wireless communication are provided. In one aspect, an example method may include determining to control a bit rate of a content encoder. The method may include generating a first number of shaded texture atlases for use in rendering a second number of frames by a second device based on the determination to control the bit rate of the content encoder. Each respective shaded texture atlas may include a respective plurality of shaded primitives. The method may include encoding, by the content encoder of the first device, a first shaded texture atlas of the first number of shaded texture atlases. The method may include transmitting, by the first device, the encoded first shaded texture atlas to the second device.

Distributed graphics processing

Disclosed are a system, apparatus, and method for 3D object segmentation within an environment. Image frames are obtained from one or more depth cameras or at different times and planar segments are extracted from data obtained from the image frames. Candidate segments that comprise a non-planar object surface are identified from the extracted planar segments. In one aspect, certain extracted planar segments are identified as comprising a non-planar object surface, and are referred to as candidate segments. Confidence of preexisting candidate segments are adjusted in response to determining correspondence with a candidate segment. In one aspect, one or more preexisting candidate segments are determined to comprise a surface of a preexisting non-planar object hypothesis. Confidence in the non-planar object hypothesis is updated in response to determining correspondence with a candidate segment.

3D object segmentation

A method of recognizing an object of interest in an image includes extracting a first set of features from within the image. Each extracted feature in the first set of features is then categorized as either blob-like or edge-like. A second set of features is then taken from the first set, where a number of the edge-like features to include in the second set of features is based on a relative number of edge-like features to blob-like features included in the first set of extracted features. An object of interest within the image is detected according to the second set of features.

Adaptive edge-like feature selection during object detection

Systems, methods, and devices are described for capturing compact representations of three-dimensional objects suitable for offline object detection, and storing the compact representations as object representation in a database. One embodiment may include capturing frames of a scene, identifying points of interest from different key frames of the scene, using the points of interest to create associated three-dimensional key points, and storing key points associated with the object as an object representation in an object detection database.

Interactive and automatic 3-D object scanning method for the purpose of database creation

Systems, apparatus and methods for triggering a depth sensor and/or limiting bandwidth and/or maintaining privacy are presented. By limiting use of a depth sensor to times when an optical image alone is insufficient, mobile device power is saved. Furthermore, by reducing a size of an optical image to only the portion of the image needed to detect an object, bandwidth is saved and privacy is maintained by not communicating unneeded or undesired information.

Strategies for triggering depth sensors and transmitting RGBD images in a cloud-based object recognition system

Growing community of inventors

San Diego, CA, United States of America

Bojan Vrcelj