Abstract: A method, device, and apparatus for synthesizing a motion sequence of a virtual object and a non-transitory computer-readable storage medium are disclosed. The method can include obtaining description information of a motion sequence of a virtual object, and determining a continuous motion clip set similar to at least some motions in the motion sequence based on the description information and a continuous motion clip library constructed with video materials. The method can further include synthesizing the motion sequence of the virtual object based on the continuous motion clip set, where each continuous motion clip in the continuous motion clip library includes a unique identifier of the continuous motion clip, motion information of the continuous motion clip, and a representation vector corresponding to the each continuous motion clip.

Abstract: A projection apparatus according to the present invention, includes: a projection optical system configured to project an input image onto a projection plane, and at least one memory and at least one processor which function as: a position-detecting unit configured to detect a position pointed to by a pointer on the projection plane; and a control unit configured to perform control so that the projection optical system projects the input image and projects a graphic at the position detected by the position-detecting unit, wherein in a case where an image is scrolled in a specific range of the input image, the control unit performs control so that the graphic corresponding to the specific range moves in a direction in accordance with the scrolling.

Abstract: A computer-implemented method for using a trained generative adversarial network to improve construction and urban planning includes receiving a semantically-segmented point cloud corresponding to a construction site; determining a volumetric soil measurement; and generating a cost estimate. A computing system for using a trained generative adversarial network to improve vehicle orientation and navigation includes one or more processors, and one or more memories having stored thereon computer-executable instructions that, when executed, cause the computing system to: receive a semantically-segmented point cloud corresponding to a construction site; determine a volumetric soil measurement; and generate a cost estimate. A non-transitory computer-readable medium includes computer-executable instructions that, when executed, cause a computer to: receive a semantically-segmented point cloud corresponding to a construction site; determine a volumetric soil measurement; and generate a cost estimate.

Abstract: Technology described herein can be embodied in a method of providing visual feedback during surgery. The method includes obtaining a set of vectors representing a model of an anatomical organ, the set produced from a representation of the organ as imaged under one or more imaging modalities. The method includes obtaining a set of pixel positions of a display device, wherein the pixel positions correspond to a view of the organ. The method further includes generating, using at least a portion of the set of vectors, multiple fragment-vectors for each pixel position in the set of pixel positions, the multiple fragment-vectors each representing a corresponding portion of the organ along a line-of-sight through the organ, and generating a pixel value for each pixel position in the set of pixel positions, and presenting, on the display device, an augmented image of the view of the organ using the generated pixel values.

Abstract: Examples of the disclosure describe systems and methods for recording augmented reality and mixed reality experiences. In an example method, an image of a real environment is received via a camera of a wearable head device. A pose of the wearable head device is estimated, and a first image of a virtual environment is generated based on the pose. A second image of the virtual environment is generated based on the pose, wherein the second image of the virtual environment comprises a larger field of view than a field of view of the first image of the virtual environment. A combined image is generated based on the second image of the virtual environment and the image of the real environment.

Abstract: A first video generator generates first information for displaying, as a first video, a character object of a first user and a first object. A second video generator displays the first object and a third object different from the second object. An association portion associates the character object of the first user with a fourth object associated with the third object when the character object of the first user and the third object have a predetermined relationship. The second video generator displays the fourth object in association with the character object of the first user when the fourth object is associated with the character object of the first user by the association portion.

Abstract: The method performed at an electronic device including one or more processors, a non-transitory memory, and a depth sensor includes: obtaining a task associated with a physical object within a physical environment; obtaining a task associated with a physical object within a physical environment; obtaining depth information, via the depth sensor, associated with the physical environment; determining one or more measurements for the physical object based at least in part on the depth information; generating a graphical overlay for the task based at least in part on the task associated with the physical object and the one or more measurements for the physical object; and causing presentation of the graphical overlay relative to a representation of the physical object, wherein the representation is obtained using sensor readings of the physical object.

Abstract: Font recommendation techniques are described that provide recommendations of fonts based on a variety of factors, automatically and without user intervention in real time. This is performable in a variety of ways by addressing a wide range of considerations as part of machine learning, examples of which include context, popularity, similarity, customization, and topic compatibility.

Abstract: In implementations of systems for generating spacing guides for objects in perspective views, a computing device implements a guide system to determine groups of line segments of perspective bounding boxes of objects displayed in a user interface of a digital content editing application. Interaction data is received describing a user interaction with a particular object of the objects displayed in the user interface. The guide system identifies a particular group of the groups of line segments based on a line segment of a perspective bounding box of the particular object. An indication of a guide is generated for display in the user interface based on the line segment and a first line segment included in the particular group.

Abstract: Various implementations disclosed herein include devices, systems, and methods that generates a three-dimensional (3D) model based on a selected subset of the images and depth data corresponding to each of the images of the subset. For example, an example process may include acquiring sensor data during movement of the device in a physical environment including an object, the sensor data including images of a physical environment captured via a camera on the device, selecting a subset of the images based on assessing the images with respect to motion-based defects based on device motion and depth data, and generating a 3D model of the object based on the selected subset of the images and depth data corresponding to each of the images of the selected subset.

Abstract: Apparatuses, systems, and techniques to animate objects in computer-generated graphics. In at least one embodiment, one or more neural networks are trained to identify one or more forces to be applied to one or more objects based, at least in part, on training data corresponding to two or more aspects of motion of the one or more objects.

Abstract: Disclosed herein is a web-based videoconference system that allows for multi-screen sharing. In some embodiments, data specifying a three-dimensional virtual space is received. The three-dimensional virtual space comprises a plurality of participants and an avatar representing each of the plurality of participants and three-dimensional models of a plurality of presentation screens. Multiple presentation streams may be shared on different presentation screens simultaneously.

Abstract: In one embodiment, a method includes, by an electromagnetic device, emitting optical radiation on one or more objects disposed inside an interior of the electronic device, where the optical radiation is emitted by one or more radiation sources, capturing a set of 2D images of the one or more objects illuminated by the optical radiation, where variation of illumination or of an imaging process permits the set of 2D images to be combined into a representation of the one or more objects, determining whether the set of images comprises a representation of the one or more objects as imaged, in response to determining that the set of images comprises a representation of the one or more objects as imaged, generating a three-dimensional (3D) spectral data cube of the one or more first objects based on spectral information of the first set of images, and storing the 3D spectral data cube for processing by the electronic device.

Abstract: The present disclosure relates to a method for 3D reconstruction from satellite imagery using deep learning, said method comprising providing (101) at least two overlapping 2D satellite images, providing (102) imaging device parameters for the at least two overlapping 2D satellite images, providing (103) at least one trained Machine Learning Network, MLN, able to predict depth maps, said trained MLN being trained on a training set comprising multi-view geocoded 3D ground truth data and predicting (104) a depth map of the at provided at least two 2D satellite images using the trained at least one MLN and based on the corresponding imaging device parameters.

Abstract: In various examples, information may be received for a 3D model, such as 3D geometry information, lighting information, and material information. A machine learning model may be trained to disentangle the 3D geometry information, the lighting information, and/or material information from input data to provide the information, which may be used to project geometry of the 3D model onto an image plane to generate a mapping between pixels and portions of the 3D model. Rasterization may then use the mapping to determine which pixels are covered and in what manner, by the geometry. The mapping may also be used to compute radiance for points corresponding to the one or more 3D models using light transport simulation. Disclosed approaches may be used in various applications, such as image editing, 3D model editing, synthetic data generation, and/or data set augmentation.

Abstract: Methods and tiling engines for tiling primitives in a tile based graphics processing system in which a rendering space is divided into a plurality of tiles. The method includes generating a multi-level hierarchy of tile groups, each level of the multi-level hierarchy comprising one or more tile groups comprising one or more of the plurality of tiles; receiving a plurality of primitive blocks, each primitive block comprising geometry data for one or more primitives; associating each of the plurality of primitive blocks with one or more of the tile groups up to a maximum number of tile groups such that if at least one primitive of a primitive block falls, at least partially, within the bounds of a tile, the primitive block is associated with at least one tile group that includes that tile; and generating a control stream for each tile group based on the associations, wherein each control stream comprises a primitive block entry for each primitive block associated with the corresponding tile group.

Abstract: A video acquisition method, an electronic device, and a storage medium are disclosed. The video acquisition method is applicable to a virtual scene including at least one virtual object and at least one virtual camera. The terminal determines a target virtual object from the at least one virtual object in response to a camera capturing instruction triggered by a user on a virtual scene interface, controls the at least one virtual camera to capture the target virtual object to acquire capturing data of the target virtual object, and acquires the video of the target virtual object based on the capturing data.

Abstract: The disclosure relates to a system and a method for generating a neural network model for image processing by interacting with at least one client terminal. The method may include receiving via a network, a plurality of first training samples from the at least one client terminal. The method may also include training a first neural network model based on the plurality of first training samples to generate a second neural network model. The method may further include transmitting, via the network, the second neural network model to the at least one client terminal.

Abstract: Users create, change, duplicate, move and define interactions and relationships for digital objects in extended reality environments by voice commands in conjunction with hand or control input pointing and/or gesturing.

Abstract: One variation of a method includes: accessing a 2D color image recorded by a 2D color camera and a 3D point cloud recorded by a 3D depth sensor at approximately a first time, the 2D color camera and the 3D depth sensor defining intersecting fields of view and facing outwardly from an autonomous vehicle; detecting a cluster of points in the 3D point cloud representing a continuous surface approximating a plane; isolating a cluster of color pixels in the 2D color image depicting the continuous surface; projecting the cluster of color pixels onto the plane to define a set of synthetic 3D color points in the 3D point cloud, the cluster of points and the set of synthetic 3D color points representing the continuous surface; and rendering points in the 3D point cloud and the set of synthetic 3D color points on a display.