Abstract: Techniques and systems are provided for attention evaluation by an extended reality system. In some examples, the system determines one or more regions of interest (ROI) for an image displayed to a user. The system may also receive eye tracking information indicating an area of the image that the user is looking at. The system may further generate focus statistics based on the area of the image at which the user is looking at and the one or more ROI; and output the generated focus statistics.

Abstract: Systems and techniques are provided for synchronizing a frame rate of pass-through content from a camera and a display refresh rate. An example method can include obtaining first and second frames captured by an image capture device (which may be part of a device, such as an extended reality (XR) device). A display refresh rate of a display is greater than a camera frame rate of the image capture device. The method may determine motion between the first frame and the second frame. The method can include predicting, based on the second frame and the determined motion, a third frame corresponding to a time after the second frame. The method can include displaying content (e.g., mixed reality content) including the predicted third frame and virtual content rendered for the XR device.

Abstract: A method by a wearable device is described. The method includes receiving geometric information from a controller. The geometric information includes a point cloud and a key frame of the controller. The method also includes receiving first six degree of freedom (6DoF) pose information from the controller. The method further includes synchronizing a coordinate system of the wearable device with a coordinate system of the controller based on the point cloud and the key frame of the controller. The method additionally includes rendering content in an application based on the first 6DoF pose information.

Abstract: Techniques can conduct online visual searches through an augmented reality (AR) device having an optical see-through head mounted display (HMD). An apparatus identifies a portion of an object in a field of view of the HMD based on user interaction with the HMD. The portion includes searchable content, such as a barcode. The user interaction may be an eye gaze or a gesture. A user interaction point in relation to the HMD screen is tracked to locate a region of the object that includes the portion and the portion is detected within the region. The apparatus captures an image of the portion. The identified portion of the object does not encompass the entirety of the object. Accordingly, the size of the image is less than the size of the object in the field of view. The apparatus transmits the image to a visual search engine.

Abstract: A method by a wearable device is described. The method includes receiving geometric information from a controller. The geometric information includes a point cloud and a key frame of the controller. The method also includes receiving first six degree of freedom (6DoF) pose information from the controller. The method further includes synchronizing a coordinate system of the wearable device with a coordinate system of the controller based on the point cloud and the key frame of the controller. The method additionally includes rendering content in an application based on the first 6DoF pose information.

Abstract: Aspects of the disclosed technology relate to an apparatus including a memory and at least one processor. The at least one processor can obtain at least one image of a scene and determine a portion of interest within the scene based on a first input. The first input can include a non-touch input. The at least one processor can output, in response to the first input, content associated with the portion of interest and receive a second input from the user. The second input can include a non-eye gaze input and be associated with the content. An action can be initiated by the one or more processor based on the second input.

Abstract: Examples are described of marking specified regions of stored image frame buffer data in an image frame buffer. An imaging system can read the specified regions of the image frame buffer to identify whether the marking has been overwritten or not. The imaging system can thus efficiently identify how much of the image frame buffer has been overwritten with data from a new image frame. Based on this, the imaging system can retrieve partial image frame data from the image frame buffer and can process the partial image frame data, for instance to composite the partial image frame data with virtual content and/or to perform distortion compensation. The processed partial image frame data can be uploaded to a display buffer and displayed by a display, either as-is or once more of the frame is captured and processed. The imaging system can also perform auto-exposure using the partial image frame data.

Abstract: Examples are described of marking specified regions of stored image frame buffer data in an image frame buffer. An imaging system can read the specified regions of the image frame buffer to identify whether the marking has been overwritten or not. The imaging system can thus efficiently identify how much of the image frame buffer has been overwritten with data from a new image frame. Based on this, the imaging system can retrieve partial image frame data from the image frame buffer and can process the partial image frame data, for instance to composite the partial image frame data with virtual content and/or to perform distortion compensation. The processed partial image frame data can be uploaded to a display buffer and displayed by a display, either as-is or once more of the frame is captured and processed. The imaging system can also perform auto-exposure using the partial image frame data.

Abstract: Systems, methods, and non-transitory media are provided for extended reality (XR) control of smart devices. An example method can include generating, by a first computing device, a cryptographic key; outputting, by the first computing device, a pattern that encodes the cryptographic key, the pattern including a visual pattern, an audio pattern, and/or a light pattern; receiving, by the first computing device from a second computing device, a signed message including a command to modify an operation of the first computing device; determining, by the first computing device, whether the signed message is signed with the cryptographic key encoded in the pattern; and based on a determination that the signed message is signed with the cryptographic key encoded in the pattern, modifying the operation of the first computing device according to the command in the signed message.

Abstract: Examples are described of marking specified regions of stored image frame buffer data in an image frame buffer. An imaging system can read the specified regions of the image frame buffer to identify whether the marking has been overwritten or not. The imaging system can thus efficiently identify how much of the image frame buffer has been overwritten with data from a new image frame. Based on this, the imaging system can retrieve partial image frame data from the image frame buffer and can process the partial image frame data, for instance to composite the partial image frame data with virtual content and/or to perform distortion compensation. The processed partial image frame data can be uploaded to a display buffer and displayed by a display, either as-is or once more of the frame is captured and processed. The imaging system can also perform auto-exposure using the partial image frame data.

Abstract: The present disclosure relates to methods and devices for motion estimation which may include a GPU. In one aspect, the GPU may generate at least one first motion vector in a first subset of a frame, the first motion vector providing a first motion estimation for image data in the first subset of the frame. The GPU may also perturb the image data. Also, the GPU may generate at least one second motion vector based on the perturbed image data, the second motion vector providing a second motion estimation for the image data. Moreover, the GPU may compare the first motion vector and the second motion vector. Further, the GPU may determine at least one third motion vector for the motion estimation of the image data based on the comparison between the first motion vector and the second motion vector.

Abstract: Aspects of the disclosed technology relate to an apparatus including a memory and at least one processor. The at least one processor can obtain at least one image of a scene and determine a portion of interest within the scene based on a first input. The first input can include a non-touch input. The at least one processor can output, in response to the first input, content associated with the portion of interest and receive a second input from the user. The second input can include a non-eye gaze input and be associated with the content. An action can be initiated by the one or more processor based on the second input.

Abstract: A method, an apparatus, and a computer program product conduct online visual searches through an augmented reality (AR) device having an optical see-through head mounted display (HMD). An apparatus identifies a portion of an object in a field of view of the HMD based on user interaction with the HMD. The portion includes searchable content, such as a barcode. The user interaction may be an eye gaze or a gesture. A user interaction point in relation to the HMD screen is tracked to locate a region of the object that includes the portion and the portion is detected within the region. The apparatus captures an image of the portion. The identified portion of the object does not encompass the entirety of the object. Accordingly, the size of the image is less than the size of the object in the field of view. The apparatus transmits the image to a visual search engine.

Abstract: The present disclosure relates to methods and apparatus for display or graphics processing. Aspects of the present disclosure can determine a communication compatibility of one or more client devices. Further, aspects of the present disclosure can modify a user space or a kernel based on the communication compatibility of each of the one or more client devices. Additionally, aspects of the present disclosure can communicate at least some data with the one or more client devices based on the modified user space or the modified kernel. Aspects of the present disclosure can also modify the kernel based on the communication compatibility of each of the one or more client devices. Aspects of the present disclosure can also extend the kernel based on the communication compatibility.

Abstract: An apparatus is configured to render graphics content to reduce latency of the graphics content. The apparatus includes a display configured to present graphics content including a first portion corresponding to an area of interest and further including a second portion. The apparatus further includes a fovea estimation engine configured to generate an indication of the area of interest based on scene information related to the graphics content. The apparatus further includes a rendering engine responsive to the fovea estimation engine. The rendering engine is configured to perform a comparison of a first result of an evaluation metric on part of the area of interest with a second result of the evaluation metric with another part of the area of interest. The rendering engine is further configured to render the graphics content using predictive adjustment to reduce latency based on the comparison.

Abstract: The present disclosure relates to methods and devices for motion estimation which may include a GPU. In one aspect, the GPU may generate at least one first motion vector in a first subset of a frame, the first motion vector providing a first motion estimation for image data in the first subset of the frame. The GPU may also perturb the image data. Also, the GPU may generate at least one second motion vector based on the perturbed image data, the second motion vector providing a second motion estimation for the image data. Moreover, the GPU may compare the first motion vector and the second motion vector. Further, the GPU may determine at least one third motion vector for the motion estimation of the image data based on the comparison between the first motion vector and the second motion vector.

Abstract: An apparatus is configured to render graphics content to reduce latency of the graphics content. The apparatus includes a display configured to present graphics content including a first portion corresponding to an area of interest and further including a second portion. The apparatus further includes a fovea estimation engine configured to generate an indication of the area of interest based on scene information related to the graphics content. The apparatus further includes a rendering engine responsive to the fovea estimation engine. The rendering engine is configured to perform a comparison of a first result of an evaluation metric on part of the area of interest with a second result of the evaluation metric with another part of the area of interest. The rendering engine is further configured to render the graphics content using predictive adjustment to reduce latency based on the comparison.

Abstract: An apparatus is configured to render graphics content to reduce latency of the graphics content. The apparatus includes a display configured to present graphics content including a first portion corresponding to an area of interest and further including a second portion. The apparatus further includes a fovea estimation engine configured to generate an indication of the area of interest based on scene information related to the graphics content. The apparatus further includes a rendering engine responsive to the fovea estimation engine. The rendering engine is configured to perform a comparison of a first result of an evaluation metric on part of the area of interest with a second result of the evaluation metric with another part of the area of interest. The rendering engine is further configured to render the graphics content using predictive adjustment to reduce latency based on the comparison.

Abstract: A method, an apparatus, and a computer program product conduct online visual searches through an augmented reality (AR) device having an optical see-through head mounted display (HMD). An apparatus identifies a portion of an object in a field of view of the HMD based on user interaction with the HMD. The portion includes searchable content, such as a barcode. The user interaction may be an eye gaze or a gesture. A user interaction point in relation to the HMD screen is tracked to locate a region of the object that includes the portion and the portion is detected within the region. The apparatus captures an image of the portion. The identified portion of the object does not encompass the entirety of the object. Accordingly, the size of the image is less than the size of the object in the field of view. The apparatus transmits the image to a visual search engine.

Abstract: A method, an apparatus, and a computer program product conduct online visual searches through an augmented reality (AR) device having an optical see-through head mounted display (HMD). An apparatus identifies a portion of an object in a field of view of the HMD based on user interaction with the HMD. The portion includes searchable content, such as a barcode. The user interaction may be an eye gaze or a gesture. A user interaction point in relation to the HMD screen is tracked to locate a region of the object that includes the portion and the portion is detected within the region. The apparatus captures an image of the portion. The identified portion of the object does not encompass the entirety of the object. Accordingly, the size of the image is less than the size of the object in the field of view. The apparatus transmits the image to a visual search engine.