Abstract: Various embodiments of the present invention relate generally to systems and methods for artificially rendering images using viewpoint interpolation and extrapolation. According to particular embodiments, a method includes moving a set of control points perpendicular to a trajectory between a first frame and a second frame, where the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location. The set of control points is associated with a layer and each control point is moved based on an associated depth of the control point. The method also includes generating an artificially rendered image corresponding to a third location outside of the trajectory by extrapolating individual control points using the set of control points for the third location and extrapolating pixel locations using the individual control points.

Abstract: Provided are mechanisms and processes for visual feature tagging in multi-view interactive digital media representations (MIDMRs). In one example, a process includes receiving a visual feature tagging request that includes an MIDMR of an object to be searched, where the MIDMR includes spatial information, scale information, and different viewpoint images of the object. A visual feature in the MIDMR is identified, and visual feature correspondence information is created that links information identifying the visual feature with locations in the viewpoint images. At least one image associated with the MIDMR is transmitted in response to the feature tagging request.

Abstract: Various embodiments of the present invention relate generally to systems and processes for transforming a style of video data. In one embodiment, a neural network is used to interpolate native video data received from a camera system on a mobile device in real-time. The interpolation converts the live native video data into a particular style. For example, the style can be associated with a particular artist or a particular theme. The stylized video data can viewed on a display of the mobile device in a manner similar to which native live video data is output to the display. Thus, the stylized video data, which is viewed on the display, is consistent with a current position and orientation of the camera system on the display.

Abstract: Various embodiments of the present invention relate generally to systems and methods for artificially rendering images using viewpoint interpolation and extrapolation. According to particular embodiments, a method includes moving a set of control points perpendicular to a trajectory between a first frame and a second frame, where the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location. The set of control points is associated with a layer and each control point is moved based on an associated depth of the control point. The method also includes generating an artificially rendered image corresponding to a third location outside of the trajectory by extrapolating individual control points using the set of control points for the third location and extrapolating pixel locations using the individual control points.

Abstract: The pose of an object may be estimated based on fiducial points identified in a visual representation of the object. Each fiducial point may correspond with a component of the object, and may be associated with a first location in an image of the object and a second location in a 3D space. A 3D skeleton of the object may be determined by connecting the locations in the 3D space, and the object's pose may be determined based on the 3D skeleton.

Abstract: Various embodiments describe systems and processes for capturing and generating multi-view interactive digital media representations (MIDMRs). In one aspect, a method for automatically generating a MIDMR comprises obtaining a first MIDMR and a second MIDMR. The first MIDMR includes a convex or concave motion capture using a recording device and is a general object MIDMR. The second MIDMR is a specific feature MIDMR. The first and second MIDMRs may be obtained using different capture motions. A third MIDMR is generated from the first and second MIDMRs, and is a combined embedded MIDMR. The combined embedded MIDMR may comprise the second MIDMR being embedded in the first MIDMR, forming an embedded second MIDMR. The third MIDMR may include a general view in which the first MIDMR is displayed for interactive viewing by a user on a user device. The embedded second MIDMR may not be viewable in the general view.

Abstract: Provided are mechanisms and processes for inserting a visual element into a multi-view digital media representation (MVIDMR). In one example, a process includes analyzing an MVIDMR to determine if there is an appropriate location to insert a visual element. Once a location is found, the type of visual element appropriate for the location is determined, where the type of visual element includes either a three-dimensional object to be inserted in the MVIDMR or a two-dimensional image to be inserted as or projected onto a background or object in the MVIDMR. A visual element that is appropriate for the location is then retrieved and inserted into the MVIDMR, such that the visual element is integrated into the MVIDMR and navigable by a user.

Abstract: Images of an object may be captured at a computing device. Each of the images may be captured from a respective viewpoint based on image capture configuration information identifying one or more parameter values. A multiview image digital media representation of the object may be generated that includes some or all of the images of the object and that is navigable in one or more dimensions.

Abstract: Provided are mechanisms and processes for visual feature tagging in multi-view interactive digital media representations (MIDMRs). In one example, a process includes receiving a visual feature tagging request that includes an MIDMR of an object to be searched, where the MIDMR includes spatial information, scale information, and different viewpoint images of the object. A visual feature in the MIDMR is identified, and visual feature correspondence information is created that links information identifying the visual feature with locations in the viewpoint images. At least one image associated with the MIDMR is transmitted in response to the feature tagging request.

Abstract: A multi-view interactive digital media representation (MVIDMR) of an object can be generated from live images of an object captured from a camera. Selectable tags can be placed at locations on the object in the MVIDMR. When the selectable tags are selected, media content can be output which shows details of the object at location where the selectable tag is placed. A machine learning algorithm can be used to automatically recognize landmarks on the object in the frames of the MVIDMR and a structure from motion calculation can be used to determine 3-D positions associated with the landmarks. A 3-D skeleton associated with the object can be assembled from the 3-D positions and projected into the frames associated with the MVIDMR. The 3-D skeleton can be used to determine the selectable tag locations in the frames of the MVIDMR of the object.

Abstract: Various embodiments describe systems and processes for capturing and generating multi-view interactive digital media representations (MIDMRs). In one aspect, a method for automatically generating a MIDMR comprises obtaining a first MIDMR and a second MIDMR. The first MIDMR includes a convex or concave motion capture using a recording device and is a general object MIDMR. The second MIDMR is a specific feature MIDMR. The first and second MIDMRs may be obtained using different capture motions. A third MIDMR is generated from the first and second MIDMRs, and is a combined embedded MIDMR. The combined embedded MIDMR may comprise the second MIDMR being embedded in the first MIDMR, forming an embedded second MIDMR. The third MIDMR may include a general view in which the first MIDMR is displayed for interactive viewing by a user on a user device. The embedded second MIDMR may not be viewable in the general view.

Abstract: Orientation data for image data of an object may be determined. The orientation information may identify camera location and orientation for image data with respect to an object model represented the object at a point in time. A change to the object between different points in time may be identified by identifying a difference in image data associated with different points in time. The change may be presented in a visual representation of the object model in a user interface displayed on a display screen.

Abstract: Mappings are determined between viewpoints of an object and an object model representing the object. Each mapping identifies a location on the object model corresponding with a portion of the object captured in one of the viewpoints. Tags for the object model are created based on the mappings, where each tag links one of the viewpoints to one of the locations on the object model. A user interface that includes the object model and the tags is provided for presentation on a display screen in a user interface. One of the viewpoints is presented in the user interface when the corresponding tag is selected in the object model.

Abstract: A three-dimensional representation of a scene captured in an action shot base video may be determined. The three-dimensional representation may identify a camera pose. A representation of an object may be determined from a multi-view representation of the object that includes images of the object and that is navigable in one or more dimensions. An action shot video of the scene that includes a rendering of the object determined based on the representation and the camera pose may be generated.

Abstract: A background scenery portion may be identified in each of a plurality of image sets of an object, where each image set includes images captured simultaneously from different cameras. A correspondence between the image sets may determined, where the correspondence tracks control points associated with the object and present in multiple images. A multi-view interactive digital media representation of the object that is navigable in one or more dimensions and that includes the image sets may be generated and stored.

Abstract: Provided are mechanisms and processes for inserting a visual element into a multi-view digital media representation (MVIDMR). In one example, a process includes analyzing an MVIDMR to determine if there is an appropriate location to insert a visual element. Once a location is found, the type of visual element appropriate for the location is determined, where the type of visual element includes either a three-dimensional object to be inserted in the MVIDMR or a two-dimensional image to be inserted as or projected onto a background or object in the MVIDMR. A visual element that is appropriate for the location is then retrieved and inserted into the MVIDMR, such that the visual element is integrated into the MVIDMR and navigable by a user.

Abstract: Reference images of an object may be mapped to an object model to create a reference object model representation. Evaluation images of the object may also be mapped to the object model via the processor to create an evaluation object model representation. Object condition information may be determined by comparing the reference object model representation with the evaluation object model representation. The object condition information may indicate one or more differences between the reference object model representation and the evaluation object model representation. A graphical representation of the object model that includes the object condition information may be displayed on a display screen.

Abstract: A plurality of images may be analyzed to determine an object model. The object model may have a plurality of components, and each of the images may correspond with one or more of the components. Component condition information may be determined for one or more of the components based on the images. The component condition information may indicate damage incurred by the object portion corresponding with the component.

Abstract: A multi-view interactive digital media representation (MVIDMR) of an object can be generated from live images of an object captured from a camera. Selectable tags can be placed at locations on the object in the MVIDMR. When the selectable tags are selected, media content can be output which shows details of the object at location where the selectable tag is placed. A machine learning algorithm can be used to automatically recognize landmarks on the object in the frames of the MVIDMR and a structure from motion calculation can be used to determine 3-D positions associated with the landmarks. A 3-D skeleton associated with the object can be assembled from the 3-D positions and projected into the frames associated with the MVIDMR. The 3-D skeleton can be used to determine the selectable tag locations in the frames of the MVIDMR of the object.

Abstract: Various embodiments disclosed herein relate to systems and methods for analyzing and manipulating images and video. Methods as disclosed herein may include retrieving, using a processor, a multi-view interactive digital media representation (MIDMR) from a storage location, the MIDMR including a content model and a context model, the content model characterizing an object, and the context model characterizing scenery surrounding the object. The methods may also include receiving, using the processor, at least one dynamic content input associated with the retrieved MIDMR, the dynamic content input being received while a user is interacting with the MIDMR. The methods may further include implementing, using the processor, one or more modifications associated with the MIDMR based, at least in part, on the received at least one dynamic content input, the one or more modifications modifying a presentation and functionality of the MIDMR.