Abstract: A virtual puppeteering system includes a portable device including a camera, a display, a hardware processor, and a system memory storing an object animation software code. The hardware processor is configured to execute the object animation software code to, using the camera, generate an image in response to receiving an activation input, using the display, display the image, and receive a selection input selecting an object shown in the image. The hardware processor is further configured to execute the object animation software code to determine a distance separating the selected object from the portable device, receive an animation input, identify, based on the selected object and the received animation input, a movement for animating the selected object, generate an animation of the selected object using the determined distance and the identified movement, and render the animation of the selected object.

Abstract: Systems and methods for generating a three-dimensional reconstruction from a two-dimensional image of an asset are described. In some aspects, at least one computer hardware processor is used to perform: receiving a two-dimensional input image of an asset; encoding, using a first statistical model, the input image into a latent vector; and generating, using a second statistical model, at least one depth image from the latent vector, wherein pixel values in the at least one depth image correspond to coordinates of a point cloud.

Abstract: Described herein are methods and systems for remote visualization of real-time three-dimensional (3D) facial animation with synchronized voice. A sensor captures frames of a face of a person, each frame comprising color images of the face, depth maps of the face, voice data associated with the person, and a timestamp. The sensor generates a 3D face model of the person using the depth maps. A computing device receives the frames of the face and the 3D face model. The computing device preprocesses the 3D face model. For each frame, the computing device: detects facial landmarks using the color images; matches the 3D face model to the depth maps using non-rigid registration; updates a texture on a front part of the 3D face model using the color images; synchronizes the 3D face model with a segment of the voice data using the timestamp; and transmits the synchronized 3D face model and voice data to a remote device.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for generating an avatar based on trip information. The program and method include determining that one or more criteria associated with a user correspond to a trip taken by the user during a given time interval; retrieving a plurality of media generated by a client device of the user during the given time interval; automatically selecting a plurality of avatar customizations to represent the trip based on the plurality of media generated by the user during the given time interval; automatically generating a trip-based avatar for the user based on the plurality of avatar customizations; and causing display of the trip-based avatar.

Abstract: Briefly, in accordance with one or more embodiments, a processor performs a coarse depth test on pixel data, and performs a final depth test on the pixel data. Coarse depth data is stored in a coarse depth cache, and per pixel depth data is stored in a per pixel depth cache. If a result of the coarse depth test is ambiguous, the processor is to read the per pixel depth data from the per pixel depth cache, and to update the coarse depth data with the per pixel depth data if the per pixel depth data has a smaller depth range than the coarse depth data.

Abstract: A method for rendering a computer image includes, for each pixel of a plurality of N×M pixels forming a tile, determining a plurality of masks for the pixel, wherein N and M denote integers larger than 1, and wherein each mask identifies a respective subset of the pixels that are equidistant from the pixel and located at a respective distance from the pixel. The method further includes: determining an active mask for the tile, the active mask identifying active pixels of the pixels, each of the active pixels being determined as having color information; based on the active mask, identifying an empty pixel of the pixels, the empty pixel lacking color information; and determining at least a first nearest active pixel that is nearest to the empty pixel. The determining includes comparing the active mask with at least one mask of the masks for the empty pixel.

Abstract: The system obtains an indication of a shape of a cross-section of an elongated shape, and an orientation of the shape. Based on the shape of the cross-section of the elongated shape and the orientation of the shape, the system creates a nonuniform distribution of random numbers mapping uniformly distributed input values to multiple points on the surface of the elongated shape. The system provides an input value randomly selected from a uniform distribution of random numbers to the nonuniform distribution of random numbers to obtain a point among the multiple sample points on the surface of the elongated shape. The system applies a function to the input value to obtain an indication of a normal associated with the sample point among the multiple sample points. Finally, the system computes an illumination of the elongated shape using the normal.

Abstract: A method and an intersection testing module in a ray tracing system for performing intersection testing for a ray with respect to a plurality of convex polygons, each of which is defined by an ordered set of vertices, wherein at least one of the vertices is a shared vertex which is used to define at least two of the convex polygons. The vertices of the convex polygons are projected onto a pair of axes orthogonal to the ray direction. A vertex ordering scheme defines an ordering of the projected vertices which is independent of the ordering of the vertices in the ordered sets.

Abstract: A shadow rendering method for an image includes: re-projecting 3D coordinates of image pixels from an image space of the image to points on a 2D shadowmap space; estimating at least one of a horizontal and vertical distribution of the points in the shadow map space; for a flexible scale rasteriser ‘FSR’, updating a horizontal or vertical FSR curve corresponding to a distribution of FSR bins for the shadow map so that the corresponding horizontal or vertical distribution of points per bin is most even; and rendering the shadow map using flexible scale rasterization.

Abstract: Disclosed herein is a web-based videoconference system that allows for video avatars to navigate within a virtual environment. Various methods for efficient modeling, rendering, and shading are disclosed herein.

Abstract: An apparatus and method are described for utilizing volume proxies. For example, one embodiment of an apparatus comprises: a volume subdivision module to subdivide a volume into a plurality of partitions, the apparatus to process a first of the partitions and to distribute data associated with each of the other partitions to each of a plurality of nodes; a proxy generation module to compute a first proxy for the first partition, the first proxy to be transmitted to the plurality of nodes; and a ray tracing engine to perform one or more traversal/intersection operations for a current ray or group of rays using the first proxy; if the ray or group of rays interacts with the first proxy, then the ray tracing engine to send the ray(s) to a second node associated with the first proxy or retrieves data related to the interaction from the second node.

Abstract: A multi-characteristic remeshing system that generates remeshed 3D graphical surfaces can include a compact geometric descriptive language (“CGDL”) conversion module, one or more geometric characteristic parsing modules, and a geometric computation module. The CGDL conversion module receives an input mesh for a 3D graphical object and CGDL source text that describes target characteristics of an output mesh of the 3D graphical object. Each geometric characteristic parsing module identifies inherent geometric characteristics of the input mesh, and generates a geometric characteristic map. The geometric characteristic map includes instructions to generate the output mesh with respective target characteristics. The instruction describes a relationship of the one or more inherent geometric characteristics with the respective target characteristic.

Abstract: This application discloses a shadow rendering method and apparatus, a computer device, and a storage medium, the method including: obtaining at least one rendering structure in a virtual scene according to an illumination direction in the virtual scene; obtaining model coordinates of a plurality of pixels according to a current viewing angle associated with the virtual scene and depth information of the plurality of pixels; sampling at least one shadow map according to the model coordinates of the plurality of pixels to obtain a plurality of sampling points corresponding to the plurality of pixels; and rendering the plurality of sampling points in the virtual scene to obtain at least one shadow associated with the at least one virtual object.

Abstract: There is provided an image processing apparatus and an image processing method that are capable of suppressing an increase in loads when a point cloud is generated from a mesh. Point cloud data is generated by positioning points at intersection points between a surface of a mesh and vectors each including, as a start origin, position coordinates corresponding to a specified resolution. For example, intersection determination is performed between the surface of the mesh and each of the vectors, and in a case where the surface and the vector are determined to intersect each other, the coordinates of the intersection point are calculated. The present disclosure can be applied to an image processing apparatus, electronic equipment, an image processing method, a program, or the like.

Abstract: A system and method for volume rendering a light field, wherein the light field data is subjected to a layering scheme introducing a partitioning of the hogels into subsets. Each subset corresponding to a sub-volume of the layer volume, corresponds to the sub-region of the layer. Novel partitioning of the data combined with an efficient local memory caching technique, plenoptic downsampling strategies to reduce memory bandwidth requirements and volume rendering algorithm to produce a rendered light field image. A reduction in the total number of samples required can be obtained while still maintaining the quality of the resulting image. A method is also provided to order memory accesses aligned with ray calculations in order to maximize access coherency. Real-time layered scene decomposition can be combined with surface rendering method to create a hybrid real-time rendering method that supports rendering of scenes containing superimposed volumes and surfaces.

Abstract: A method of rendering an image of three-dimensional laser scan data is described. The method includes providing a range cube map and a corresponding image cube map generating a tessellation pattern using the range cube map and rendering an image based on the tessellation pattern by sampling the image cube map.

Abstract: Fusing online and mapped terrain estimates by using weighted grid cells that scales the values returned from online terrain and mapped terrain is disclosed. Previously mapped terrain data and online terrain data are fused and a grid having cells of a predetermined size is overlaid on the terrain map. Each cell may include terrain data based on weighted mapped terrain data and weighted online terrain data, where the weighting values for the mapped terrain data and for the online terrain data may be different. A fused terrain estimate may be a result of a weighted mean for each cell smoothed to reduce noise.

Abstract: A processing device is provided which includes memory and a processor. The processor is configured to receive an input image having a first resolution, generate linear down-sampled versions of the input image by down-sampling the input image via a linear upscaling network and generate non-linear down-sampled versions of the input image by down-sampling the input image via a non-linear upscaling network. The processor is also configured to convert the down-sampled versions of the input image into pixels of an output image having a second resolution higher than the first resolution and provide the output image for display.

Abstract: The technology disclosed can provide improved safety by detecting potential unsafe conditions (e.g., collisions, loss of situational awareness, etc.) confronting the user of a wearable (or portable) sensor configured to capture motion and/or determining the path of an object based on imaging, acoustic or vibrational waves. Implementations can enable improved safety to users of virtual reality for machine control and/or machine communications applications using wearable (or portable) devices, e.g., head mounted displays (HMDs), wearable goggles, watch computers, smartphones, and so forth, or mobile devices, e.g., autonomous and semi-autonomous robots, factory floor material handling systems, autonomous mass-transit vehicles, automobiles (human or machine driven), and so forth, equipped with suitable sensors and processors employing optical, audio or vibrational detection.

Abstract: An augmented reality system is disclosed. The system receives values of parameters of real-world elements of an augmented reality environment from various sensors and creates a three-dimensional textual matrix of sensor representation of a real environment world based on the parameters. The system determines a context of a specific virtual object with respect to the real-world environment based on the three-dimensional textual matrix. The system then models the specific virtual object based on the context to place the specific virtual object in the augmented reality environment.