Abstract: A 360 panoramic video sequence of an architectural or industrial site includes a plurality of 360 images. 3D poses of the 360 images are determined with respect to one another, and a subset of the images extracted for further processing according to selection criteria. The 3D poses of the extracted images is refined based on determined correspondences of the features in the images, and a 3D point cloud of the site is developed from the extracted images with refined pose estimates. An “as-built” representation of the site captured in the panoramic video sequence is created from the sparse 3D point cloud and aligned to a 2D or 3D plan of the site. Once so aligned, the extracted images may be presented to a user in conjunction with their plan positions (e.g., overlayed on the site plan). Optionally, a point cloud or mesh view of the site may also be returned.

Abstract: Adjusted overlaid images are generated in response to at least one color reference object or color reference point. A display is driven to present the adjusted overlaid image.

Abstract: A method for matching mouth shape and movement in digital video to alternative audio includes deriving a sequence of facial poses including mouth shapes for an actor from a source digital video. Each pose in the sequence of facial poses corresponds to a middle position of each audio sample. The method further includes generating an animated face mesh based on the sequence of facial poses and the source digital video, transferring tracked expressions from the animated face mesh or the target video to the source video, and generating a rough output video that includes transfers of the tracked expressions. The method further includes generating a finished video at least in part by refining the rough video using a parametric autoencoder trained on mouth shapes in the animated face mesh or the target video. One or more computers may perform the operations of the method.

Abstract: A visualized data generation device includes an acquisitor, an analyzer, and a generator. The acquisitor acquires manufacturing data including one or more pieces of first data Yi regarding a product state with respect to one product. The analyzer analyzes the first data Yi acquired by the acquisitor and derives a first index value with respect to each piece of the first data Yi. The generator generates visualized data including a first analysis result display region for causing a display device to display information about the first index value. The generator generates the visualized data in which an amount of information and a priority is set for each first analysis result display region on the basis of the first index value and a display form of the first analysis result display region is set on the basis of the amount of information and the priority.

Abstract: Modeling, constructing, and designing conformal cellular structures with spatially variable and graded microstructures that have full geometric continuity is disclosed, which includes defining a global structural domain, where the microstructures are generated for a global mesh, defining a unit structure as a base cell using a level set function, which allows for beams, trusses, shells, and solids, transforming and mapping the base cell into each element of the global mesh using an isoparametric transformation, which creates a conformal cellular structure in accordance with a set of requirements on distribution of material and/or mechanical properties, and applying a global cutting function to guarantee geometric continuity in connections on the common face of any two neighboring cells of the structure. As a result, more complex geometric shapes and features can be generated at the cell level, while maintaining the specified geometric connectivity across the cells of the structure.

Abstract: A computer-implemented method of generating a 3D model for dental simulation, comprising reading a file describing the surface of a 3D object having a volume; generating a voxel grid encompassing the 3D object, wherein the voxel grid contains a plurality of voxels; identifying a subset of voxels of the plurality of voxels which are located within the volume of the 3D object; generating a triangulated surface, wherein the triangulated surface encompasses the subset of voxels and defines the outer surface of the 3D model; assigning a density value to each voxel in the subset of voxels, wherein the subset of voxels defines the solid volume of the 3D model.

Abstract: Systems, methods, and computer readable media to manage memory cache for graphics processing are described. A processor creates a resource group for a plurality of graphics application program interface (API) resources. The processor subsequently encodes a set command that references the resource group within a command buffer and assigns a data set identifier (DSID) to the resource group. The processor also encodes a write command within the command buffer that causes the graphics processor to write data within a cache line and mark the written cache line with the DSID, a read command that causes the graphics processor to read data written into the resource group, and a de-prioritize command that causes the graphics processor to notify the memory cache to later flush content from the cache line associated with the DSID and to later invalidate the cache line when higher priority content is received.

Abstract: One embodiment provides a method comprising determining multi-dimensional metadata corresponding to an input image, and determining ambient light information indicative of a level of ambient light in an ambient environment of a display device. The multi-dimensional metadata comprises a cumulative distribution function (CDF) of pixels in the input image. The method further comprises determining, based on the multi-dimensional metadata and the ambient light information, one or more gains that adaptively compensate for the level of ambient light in the ambient environment. The method further comprises generating a tone mapping function based on the one or more gains, and applying the tone mapping function to the input image to generate a tone-mapped image that adaptively compensates for the level of ambient light in the ambient environment. The tone-mapped image is provided to the display device for presentation.

Abstract: A method and a system for generating imagery mapping modeling of goblet. The method includes: pre-process collected goblets based on a height of each goblet, and establish a sample library of goblet modeling features; perform dimension reduction processing on the imagery vocabulary, and establish a goblet user imagery adjective pair based on the processing result; a relationship between the goblet modeling and imagery adjective is obtained through the sample library of goblet modeling features and the goblet user imagery adjective pair, and an optimal imagery value is established; input an user-entered imagery value into to the established optimal goblet imagery mapping modeling model, and produces a goblet shape meets an index. It realize users' demand for imagery modeling for the goblet and provide a fast and effective new idea for updating and iterating the goblet modeling scheme with a genetic algorithm and a computer programming technology.

Abstract: A method for detecting a characteristic of a machine or component according to a time and characteristic value record includes the steps of converting a time and characteristic value record of data samples of the machine or component in a selected time window to a two-dimensional pixel bitmap in a specified pixel window, horizontal coordinates of pixel points characterizing a time sequence of data samples and vertical coordinates of pixel points characterizing quantified characteristic values of the samples, the quantified characteristic values being pixel values converted from characteristic values of individual samples using a maximum value in the window as a standard; marking the pixel bitmap according to an existing conclusion to form a sample set for training a machine learning intelligent algorithm model; and using a pixel bitmap sample in the sample set to train the algorithm model; and using the model to detect from newly collected data samples.

Abstract: A computer-implemented method of generating a 3D model for dental simulation, comprising reading a file describing the surface of a 3D object having a volume; generating a voxel grid encompassing the 3D object, wherein the voxel grid contains a plurality of voxels; identifying a subset of voxels of the plurality of voxels which are located within the volume of the 3D object; generating a triangulated surface, wherein the triangulated surface encompasses the subset of voxels and defines the outer surface of the 3D model; assigning a density value to each voxel in the subset of voxels, wherein the subset of voxels defines the solid volume of the 3D model.

Abstract: Provided is an information processing apparatus including an output control unit that controls output of an image performed by a display unit, the output control unit selecting an output image to be output by the display unit from among a plurality of candidate images based on calculated visibility of the candidate image. In addition, provided is an information processing method including causing a processor to control output of an image performed by a display unit, the control further including selecting an output image to be output by the display unit from among a plurality of candidate images based on the calculated visibility of the candidate image.

Abstract: Systems and methods for simulation of ambient light based on generated imagery are disclosed herein. Such a system can include a simulation sled, a simulation display that can display generated imagery viewable from the simulation sled, an ambient light simulator that can selectively illuminate portions of the simulation sled, and a processor. The simulation sled can include a plurality of user controls. The processor can: control the simulation display to generate imagery; identify an effect of the generated imagery on the simulation sled; and control the ambient light simulator to selectively illuminate at least portions of the simulation sled according to the identified effect of the simulated light source.

Abstract: Methods and apparatuses are disclosed herein for performing tone mapping and/or contrast enhancement. In some examples, a block mapping curve is low-pass filtered with block mapping curves of surrounding blocks to form a smoothed block mapping curve. In some examples, overlapped curve mapping of block mapping curves, including smoothed block mapping curves, is performed, including weighting, based on a pixel location, block mapping curves of a group of blocks to generate an interpolated block mapping curve and applying the interpolated block mapping curve to a pixel to perform ton mapping and/or contrast enhancement.

Abstract: The present disclosure discloses a speech-driven facial animation generation method. The method is mainly divided into six steps: extracting speech features, collecting frequency information, summarizing time information, decoding action features, driving a facial model, and sliding a signal window. The present disclosure can drive, according to an input speech audio signal, any facial model in real time under a particular delay to generate animation. The quality of the animation reaches the currently most advanced speech animation technology level, and has the characteristics of light weight and good robustness. The present disclosure can be used to generate speech animation under different scenes, such as VR virtual social networking, and virtual speech assistants and games.

Abstract: A posture prediction method includes: acquiring an action area in the scene image by acquiring a scene image obtained by scanning a three-dimensional scene, acquiring an action label corresponding to the action area, the action label is configured to represent the action performed by the human body in the action area, acquiring posture data according to the action area and the action label, acquiring a human body posture model according to the posture data, and mapping the human body posture model into the three-dimensional scene according to the action area and the posture data.

Abstract: In some embodiments, a method includes receiving an image of produce and an image of marking. The image of produce has a set of pixels, each associated with a position and a color value. The method further includes generating a grayscale image from the image of produce. The method further includes cropping out a portion from the grayscale image. The method further includes locating a marking position pixel on the image of produce by: (a) producing a list of pixels that are part of the cropped portion, (b) selecting, from the list of pixels, a subset of pixels having grayscale pixel values above a threshold, and (c) randomly selecting the marking position pixel from the subset of pixels. The method further includes overlaying the image of marking on the image of produce by coinciding a pixel of the image of marking with the marker position pixel.

Abstract: The disclosure provides a method for generating action according to an audio signal and an electronic device. The method includes: receiving an audio signal and extracting a high-level audio feature therefrom; extracting a latent audio feature from the high-level audio feature; in response to determining that the audio signal corresponds to a beat, obtaining a joint angle distribution matrix based on the latent audio feature; in response to determining that the audio signal corresponds to a music, obtaining a plurality of designated joint angles corresponding to a plurality of joint points based on the joint angle distribution matrix; and adjusting a joint angle of each of the joint points on the avatar according to the designated joint angles.

Abstract: Graphics processing in a client device includes receiving, as part of a vector streaming split rendering process, a bit stream encoding a sequence of shading atlases of the process. Each shading atlas includes blocks. The client decodes a particular shading atlas of the sequence of shading atlases, and determines that a particular block of the particular shading atlas was unsuccessfully decoded. The client identifies a stored block of a prior shading atlas of the sequence of shading atlases as a successfully decoded earlier version of the particular block. The client renders the particular shading atlas using the stored block instead of the particular block.

Abstract: Apparatuses, methods, and computer programs are disclosed. An example apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: signal a depth start of a patch data unit of a patch of data content based on an identifier of a tile and a patch index; wherein the depth start is used to derive a range of at least one depth value for the patch based on the patch index in a tile having the identifier; and signal a depth threshold of an immersive video extension of the patch data unit; wherein the depth threshold specifies a threshold below which an occupancy value is defined to be unoccupied for the patch based on the patch index.