Abstract: In various embodiments, a design exploration application generates images that represent design alternatives for three-dimensional (3D) objects. The design exploration application generates a keyword prompt based on design intent text that describes a 3D object. The design exploration application executes a first machine learning model on the keyword prompt to generate a first set of keywords. The design exploration application generates a rephrase prompt based on a second set of keywords that includes at least one keyword from the first set of keywords. The design exploration application executes the first machine learning model on the rephrase prompt to generate a final text prompt. The design exploration application executes a second machine learning model on the final text prompt to generate a set of images.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for providing editable keyframe-based animation data for applying to a character to animate motion of the character in three-dimensional space. Three-dimensional motion data is constructed from two-dimensional videos. The three-dimensional motion data represents movement of people in the two-dimensional videos and includes, for each person, a root of a three-dimensional skeleton of the person. The three-dimensional skeleton comprises multiple three-dimensional poses of the person during at least a portion of frames of a video from the two-dimensional videos. The three-dimensional motion data is converted into editable keyframe-based animation data in three-dimensional space and provided to animate motion.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for collaboration and view sharing between users when performing editing operations over a shared document. A first portion of a shared document is displayed to a first user in a user interface of a first instance of a collaboration application of a first user. The displayed first portion comprises a first location of the first user within the shared document. In the user interface, an indication specifying a relative locational direction from the first location towards a second location of a second user within the shared document is provided. A second portion of the shared document is being displayed to the second user through a second instance of the collaboration application during a conference call between a set of users, where the displayed second portion includes the second location of the second user within the shared document.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for providing editable keyframe-based animation data for applying to a character to animate motion of the character in three-dimensional space. Three-dimensional motion data is constructed from two-dimensional videos. The three-dimensional motion data represents movement of people in the two-dimensional videos and includes, for each person, a root of a three-dimensional skeleton of the person. The three-dimensional skeleton comprises multiple three-dimensional poses of the person during at least a portion of frames of a video from the two-dimensional videos. The three-dimensional motion data is converted into editable keyframe-based animation data in three-dimensional space and provided to animate motion.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design and manufacture of physical structures using toolpath generation by demonstration include, in one aspect, a method including: receiving a user specified path traced in reference to geometry of a modeled object to be manufactured by a computer-controlled manufacturing system, wherein the user specified path is a spatial representation of a desired toolpath; synthesizing candidate toolpaths for the geometry of the modeled object using variations of at least one toolpath parameter; measuring similarities between the candidate toolpaths and the user specified path, including comparing at least a spatial similarity between the candidate toolpaths and the user specified path; suggesting at least some of the candidate toolpaths based on the measured similarities; and determining a toolpath for use when manufacturing the modeled object in accordance with user input regarding the at least some of the candidat

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design and manufacture of physical structures using toolpath generation by demonstration include, in one aspect, a method including: receiving a user specified path traced in reference to geometry of a modeled object to be manufactured by a computer-controlled manufacturing system, wherein the user specified path is a spatial representation of a desired toolpath; synthesizing candidate toolpaths for the geometry of the modeled object using variations of at least one toolpath parameter; measuring similarities between the candidate toolpaths and the user specified path, including comparing at least a spatial similarity between the candidate toolpaths and the user specified path; suggesting at least some of the candidate toolpaths based on the measured similarities; and determining a toolpath for use when manufacturing the modeled object in accordance with user input regarding the at least some of the candidat

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for generating and visualizing 3D scenes include, in one aspect, a method including: obtaining metadata for 2D images that are related to a location of interest; searching for discrete image correspondences between pairs of the 2D images; grouping the 2D images into different time periods, including inferring one or more time periods for a portion of the 2D images that do not have date metadata; receiving a selection of at least one of the different time periods; finding camera intrinsic and extrinsic parameters for each image grouped into the selected time period; reconstructing a 3D scene of the location during the selected time period from the 2D images grouped into the selected time period using the camera intrinsic and extrinsic parameters; and providing the 3D scene for use in displaying the location of interest from different 3D perspectives.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for generating and visualizing 3D scenes include, in one aspect, a method including: obtaining metadata for 2D images that are related to a location of interest; searching for discrete image correspondences between pairs of the 2D images; grouping the 2D images into different time periods, including inferring one or more time periods for a portion of the 2D images that do not have date metadata; receiving a selection of at least one of the different time periods; finding camera intrinsic and extrinsic parameters for each image grouped into the selected time period; reconstructing a 3D scene of the location during the selected time period from the 2D images grouped into the selected time period using the camera intrinsic and extrinsic parameters; and providing the 3D scene for use in displaying the location of interest from different 3D perspectives.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for visualizing user interfaces. In one aspect, a method includes presenting a user interface visualization for an application. The application is configured to perform functions and present a graphical user interface including user interface elements to access the functions. Presenting the user interface visualization for the application includes selecting a group of related functions and presenting a graphical representation for each related function. The graphical representations for the related functions are presented in proximity to each other, and the graphical representations are presented differently than the user interface elements for the related functions are presented by the graphical user interface of the application.

Abstract: An interactive 3D presentation system that utilizes a collection of shots or motion views where each shot can include a combination of a camera view and camera action. A visual transition, such as a fade, can be presented at the end and beginning of sequential shots. Between the end point of a first shot and the beginning of a sequential shot, the scene is not shown. The system allows interactive authoring and/or viewing a 3D visual experience composed by defining a collection of shots where each shot is a combination of a camera view point of interest (POI) plus a camera motion path. The POI is placed on the path in a variety of ways where it can be at the beginning, in the middle or at the end of the path. A collection of predefined, cinematically styled camera motion paths, such as a crane and track shots, can be made available to the author. The pacing and duration of each shot can be adjusted.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for visualizing user interfaces. In one aspect, a method includes presenting a user interface visualization for an application. The application is configured to perform functions and present a graphical user interface including user interface elements to access the functions. Presenting the user interface visualization for the application includes selecting a group of related functions and presenting a graphical representation for each related function. The graphical representations for the related functions are presented in proximity to each other, and the graphical representations are presented differently than the user interface elements for the related functions are presented by the graphical user interface of the application.

Abstract: The present invention is a system that manages a volumetric display using volume windows. The volume windows have the typical functions, such as minimize, resize, etc., which operate in a volume. When initiated by an application a volume window is assigned to the application in a volume window data structure. Application data produced by the application is assigned to the windows responsive to which applications are assigned to which windows in the volume window data structure. Input events are assigned to the windows responsive to whether they are spatial or non-spatial. Spatial events are assigned to the window surrounding the event or cursor where a policy resolves situations where more than one window surrounds the cursor. Non-spatial events are assigned to the active or working window.

Abstract: The present invention is a system that manages a volumetric display using volume windows. The volume windows have the typical functions, such as minimize, resize, etc., which operate in a volume. When initiated by an application a volume window is assigned to the application in a volume window data structure. Application data produced by the application is assigned to the windows responsive to which applications are assigned to which windows in the volume window data structure. Input events are assigned to the windows responsive to whether they are spatial or non-spatial. Spatial events are assigned to the window surrounding the event or cursor where a policy resolves situations where more than one window surrounds the cursor. Non-spatial events are assigned to the active or working window.

Abstract: A method, apparatus, and article of manufacture provide the ability to control a three-dimensional scene view. A three-dimensional (3D) scene having one or more three-dimensional objects is displayed. A 3D representation of a coordinate system of the scene is displayed. The 3D representation contains a current viewpoint, one or more faces, one or more edges, and one or more corners with each face, edge, and corner representing a corresponding viewpoint of the scene. The 3D representation is manipulated. A new current viewpoint of the 3D representation is displayed based on the manipulation. The scene is then reoriented corresponding to the new current viewpoint based on the manipulation of the 3D representation.

Abstract: The present invention is a system that includes a tracking menu that tracks the movement of a position transducer, such as a stylus or a mouse, as the transducer is moved about in association with a display. The menu is typically displayed on top of other objects in the display. The menu includes a tracking symbol, such as an arrow or cursor, positioned corresponding to inputs from the transducer as it is moved by a user. A mobile tracking region is also included. This tracking region has a tracking boundary or edge enclosing the tracking symbol where the tracking symbol is movable within the boundary or hits without the menu moving. The tracking region or entire menu moves in correspondence to the tracking symbol when the tracking symbol encounters the boundary or hits while the symbol is moving. The tracking region also has menu controls or buttons that are activatable when the tracking symbol corresponds to the controls.

Abstract: The present invention is a system that allows a user to physically rotate a three-dimensional volumetric display enclosure with a corresponding rotation of the display contents. The rotation of the enclosure is sampled with an encoder and the display is virtually rotated by a computer maintaining the scene by an amount corresponding to the physical rotation before being rendered. This allows the user to remain in one position while viewing different parts of the displayed scene corresponding to different viewpoints. The display contents can be rotated in direct correspondence with the display enclosure or with a gain (positive or negative) that accelerates the rotation of the contents with respect to the physical rotation of the enclosure. Any display widgets in the scene, such as a virtual keyboard, can be maintained stationary with respect to the user while scene contents rotate by applying a negative rotational gain to the widgets.

Abstract: The present invention is a system that creates a volumetric display and a user controllable volumetric pointer within the volumetric display. The user can point by aiming a beam which is vector, planar or tangent based, positioning a device in three-dimensions in association with the display, touching a digitizing surface of the display enclosure or otherwise inputting position coordinates. The cursor can take a number of different forms including a ray, a point, a volume and a plane. The ray can include a ring, a bead, a segmented wand, a cone and a cylinder. The user designates an input position and the system maps the input position to a 3D cursor position within the volumetric display. The system also determines whether any object has been designated by the cursor by determining whether the object is within a region of influence of the cursor. The system also performs any function activated in association with the designation.

Abstract: A system that allows a user to spotlight a region of particular interest in a large-scale display, such as a wall panel display. The spotlight can be a circular or other shape area around which the display is de-emphasized, such as by being darkened or blurred outside the circle. The spotlight can be moved by the user moving a cursor positioned in the circle. When the cursor encounters an edge of the circle the spotlight is moved in the direction of cursor movement. As the cursor is moved the outside region has less de-emphasis. When the movement is stopped the outside region is darkened to the maximum. A spotlight beam or other attention directing area of emphasis can be used to help focus a viewer's attention on the spotlight. The spotlight can follow objects in a scene as they move.

Abstract: The system displays an image portraying a virtual space as viewed by a virtual camera at a first location on a spatially navigable camera surface within the virtual space. A user begins a drag operation. Based on the dragging, the virtual camera is spatially translated from the first location on the spatially navigable region to a second location on the spatially navigable region. The orientation of the virtual camera at the second location may be automatically set to either point towards the pre-defined look-at point or to point in a direction normal to the spatially navigable region at the second location. The system then displays an image portraying the virtual space in accordance with the location and orientation of the virtual camera at the second location in the spatially navigable camera surface. While the drag operation continues, the system determines that further translating the virtual camera would place the virtual camera beyond the spatially navigable region.

Abstract: The present invention is a system that allows a number of 3D volumetric display or output configurations, such as dome, cubical and cylindrical volumetric displays, to interact with a number of different input configurations, such as a three-dimensional position sensing system having a volume sensing field, a planar position sensing system having a digitizing tablet, and a non-planar position sensing system having a sensing grid formed on a dome. The user interacts via the input configurations, such as by moving a digitizing stylus on the sensing grid formed on the dome enclosure surface. This interaction affects the content of the volumetric display by mapping positions and corresponding vectors of the stylus to a moving cursor within the 3D display space of the volumetric display that is offset from a tip of the stylus along the vector.