Abstract: Methods and systems for generating a three-dimensional (3D) image using one or more diffusion models. The method includes obtaining input data into at least one diffusion model, in which the input data includes a prompt for generating the 3D image and generating at least two sets of two-dimensional (2D) images from a 3D representational model that is configured to render the 3D image. The method further includes determining a correspondence loss between reprojected points from the 3D representational model and cross-view correspondences from the at least one diffusion model and updating the 3D representational model based on the correspondence loss.

Abstract: A computing system displays, via a first display generation component, a computer-generated environment, and concurrently displays status information corresponding to the computing system via the second display generation component, including concurrently displaying: a visual representation of a portion of a user of the computing system who is in a position to view the computer-generated environment via the first display generation component, and one or more graphical elements that provide a visual indication of content in the computer-generated environment. The computing system detects a respective event; and in response, the computing system changes a level of immersion of the computer-generated environment displayed via the first display generation component, and changes the status information that is displayed via the second display generation component, including changing an appearance of the visual representation of the portion of the user of the computing system.

Abstract: Wearable head-mounted displays, such as virtual reality systems, present immersive experiences and environments to a wearer. However, the head-mounted displays, as well as the immersive environments that they produce, limit the wearer's ability to interact with outside observers. For example, a wearer may not be able to see outside observers, and outside observers may not have any insight to what the wearer is experiencing or where the wearer's attention is directed. Accordingly, a wearable electronic device may include an outward-facing display configured to display information to outside observers, such as images of the wearer's face or images that represent or indicate the state of the wearer and/or the head mounted display.

Abstract: An electronic device may include a lenticular display. The lenticular display may have a lenticular lens film formed over an array of pixels. The lenticular lenses may be configured to enable stereoscopic viewing of the display such that a viewer perceives three-dimensional images. The display may have a number of independently controllable viewing zones. A eye and/or head tracking system may use a camera to capture images of a viewer of the display. Control circuitry in the electronic device may use the captured images from the eye and/or head tracking system to determine which viewing zones are occupied by the viewer's eyes. The control circuitry may disable or dim viewing zones that are not occupied by the viewer's eyes in order to conserve power. An unoccupied viewing zone and an adjacent, occupied viewing zone may display the same image to increase sharpness in the display.

Abstract: In various examples, systems and methods are disclosed relating to generation of four-dimensional (4D) content models, such as 4D content models to render realistic sequences of frames of 3D data. The systems can initialize a 3D component of the 4D content model, such as a 3D Gaussian splatting representation, based at least on a prompt for the 4D content. The system can configure motion and/or dynamics for the sequence of frames by evaluating frames rendered from the 4D content model using one or more latent diffusion models (LDMs), including a video LDM. The system can perform operations such as autoregressive generation of frames to create long sequences of content, motion amplification to facilitate realistic, dynamic motion generation, and regularization to facilitate generation of complex dynamics.

Abstract: Apparatuses, systems, and techniques are presented to generate digital content. In at least one embodiment, one or more neural networks are used to generate a three-dimensional voxel representation of a scene based, at least in part, upon a plurality of two-dimensional images of the scene.

Abstract: In some embodiments, an electronic device displays and allows user interaction with content on multiple displays. In some embodiments, an electronic device displays three-dimensional content using coordinated views on multiple displays. In some embodiments, an electronic device shares content while displaying a video conferencing user interface. In some embodiments, an electronic device facilitates the display or keeping private of content on multiple displays. In some embodiments, an electronic device facilitates the display of information from applications using a shared graphical input coordinate space. In some embodiments, an electronic device presents indications of notifications. In some embodiments, an electronic device presents representations of items of content that are related to content presented on the one or more electronic devices. In some embodiments, an electronic device presents user interfaces including a soft keyboard.

Abstract: The present invention relates to an MRI-based method for predicting a degree of accumulation of a biomarker associated with Alzheimer's disease and a companion diagnosis method using same, wherein a degree of accumulation of a biomarker associated with Alzheimer's disease in each brain area of a subject can be accurately predicted using positron emission tomography (PET) or in cerebrospinal fluid (CSF) through a lumbar puncture without directly measuring an accumulated level of the biomarker associated with Alzheimer's disease, whereby the present invention can be used for diagnosis and companion diagnosis of various neurodegenerative diseases.

Abstract: An electronic device may include a stereoscopic display with a plurality of lenticular lenses that extend across the length of the display. The lenticular lenses may be configured to enable stereoscopic viewing of the display such that a viewer perceives three-dimensional images. The display may have different viewing zones that account for horizontal parallax as a viewer moves horizontally relative to the display. The display may be dimmed globally, blurred, and/or composited with a default image based on the detected vertical position of the viewer. The display may render content that compensates for the real-time vertical positions of multiple viewers.

Abstract: In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.

Abstract: In various examples, high-precision semantic image editing for machine learning systems and applications are described. For example, a generative adversarial network (GAN) may be used to jointly model images and their semantic segmentations based on a same underlying latent code. Image editing may be achieved by using segmentation mask modifications (e.g., provided by a user, or otherwise) to optimize the latent code to be consistent with the updated segmentation, thus effectively changing the original, e.g., RGB image. To improve efficiency of the system, and to not require optimizations for each edit on each image, editing vectors may be learned in latent space that realize the edits, and that can be directly applied on other images with or without additional optimizations. As a result, a GAN in combination with the optimization approaches described herein may simultaneously allow for high precision editing in real-time with straightforward compositionality of multiple edits.

Abstract: A physical keyboard can be used to collect user input in a typing mode or in a tracking mode. To use a tracking mode, first movement data is detected for a hand of a user in relation to a physical keyboard at a first location. A determination is made that the first movement data is associated with a tracking movement. In response to determining that the movement type is associated with the tracking movement, a tracking mode is initiated. User input is provided based on the movement data and in accordance with the tracking mode. Contact data and non-contact data is used to determine a user intent, and a user instruction is processed based on the user intent.

Abstract: Wearable head-mounted displays, such as virtual reality systems, present immersive experiences and environments to a wearer. However, the head-mounted displays, as well as the immersive environments that they produce, limit the wearer's ability to interact with outside observers. For example, a wearer may not be able to see outside observers, and outside observers may not have any insight to what the wearer is experiencing or where the wearer's attention is directed. Accordingly, a wearable electronic device may include an outward-facing display configured to display information to outside observers, such as images of the wearer's face or images that represent or indicate the state of the wearer and/or the head mounted display.

Abstract: Wearable head-mounted displays, such as virtual reality systems, present immersive experiences and environments to a wearer. However, the head-mounted displays, as well as the immersive environments that they produce, limit the wearer's ability to interact with outside observers. For example, a wearer may not be able to see outside observers, and outside observers may not have any insight to what the wearer is experiencing or where the wearer's attention is directed. Accordingly, a wearable electronic device may include an outward-facing display configured to display information to outside observers, such as images of the wearer's face or images that represent or indicate the state of the wearer and/or the head mounted display.

Abstract: Apparatuses, systems, and techniques to generate an image of an environment. In at least one embodiment, one or more neural networks are used to identify one or more static and dynamic features of an environment to be used to generate a representation of the environment.

Abstract: The present disclosure generally relates to updating user interfaces based on user presence and/or outputting information about detected real-world object.

Abstract: A computer input system includes a mouse including a housing having an interior surface defining an internal volume and a sensor assembly disposed in the internal volume. A processor is electrically coupled to the sensor assembly and a memory component having electronic instructions stored thereon that, when executed by the processor, causes the processor to determine an orientation of the mouse relative to a hand based on a touch input from the hand detected by the sensor assembly. The mouse can also have a circular array of touch sensors or lights that detect hand position and provide orientation information to the user.

Abstract: An input device can include a housing defining an internal volume and a lower portion, the lower portion defining an aperture, an input sensor disposed in the internal volume, and a haptic assembly disposed in the internal volume. The haptic assembly can include an actuator and a foot coupled to the actuator and aligned with the aperture. The actuator can be configured to selectively extend the foot through the aperture to vary a sliding resistance of the input device on a support surface.

Abstract: A physical keyboard can be used to collect user input in a typing mode or in a tracking mode. To use a tracking mode, first movement data is detected for a hand of a user in relation to a physical keyboard at a first location. A determination is made that the first movement data is associated with a tracking movement. In response to determining that the movement type is associated with the tracking movement, a tracking mode is initiated. User input is provided based on the movement data and in accordance with the tracking mode. Contact data and non-contact data is used to determine a user intent, and a user instruction is processed based on the user intent.

Abstract: A head-mounted device may have an inner display that displays images for a user and an outer display that informs nearby people of the status of the user and inner display. For example, the outer display may display an image of a face, an abstract layer, or both, depending on whether the inner display is operating in passthrough mode, mixed reality mode, or virtual reality mode. An ambient light sensor in the head-mounted device may be used to measure the brightness and color of ambient light. The white point of the face layer on the outer display may be adapted to the color of ambient light, whereas the white point of the abstract layer on the outer display may remain fixed. The white point of a display may be a correlated color temperature setting (e.g., measured in degrees Kelvin) that determines the warmth or coolness of displayed colors.