Abstract: A method for rendering a hair virtual model includes: obtaining particle attribute information of a hair particle in a hair particle model simulating a target hair rendering effect; obtaining a hair particle order parameter indicating an order of respective distances of each hair particle from a specified reference point in a model space; determining a target hair particle of the hair particle based on the hair particle order; and obtaining a rendered hair virtual model by determining a hair segment rendering region based on the particle attribute information of the target hair particle and rendering the hair segment rendering region to obtain a rendered hair virtual model.

Abstract: Systems and methods are provided that learn garment deformations such that they are essentially collision free. A diffused, volumetric body model representation of the underlying body together with the construction of a subspace for the garment model that yields a differentiable, canonical space configuration. This subspace is used for the regression of the garment model deformation and its dynamics. In this way, garment model deformations are predicted avoiding collisions, and the complexity for inference is reduced, such that a learned representation yields higher quality than previously achievable. The generated garments exhibit a large amount of spatial and temporal detail, and can be produced extremely quickly via the pre-trained networks.

Abstract: A control system and control method for LED string light source with fast control speeds, occupy low signal transmission capacity, and can smartly detect faults in the LED string light source, wherein comprising an LED string light provided with a plurality of LED point light sources, a power line and data control line connected between the decoder controller and each LED point light source. Address lines are used in the LED string light source to connect all address pins of the smart driver chip in series based on the numerical order of the electrical connection of the decoder controller. The smart driver chip requires rewriting the temporary address once every power-on cycle. Since the chip has a signal feedback function, users do not need specialized personnel to effectively use the decoder controller to assess the status of the point light source.

Abstract: A method for providing an immersive digital experience can include generating, at a first computing device, a virtual environment, the virtual environment including positional data for at least one digital object. The first computing device can receive first streamed motion data corresponding to real-time motion of a first physical subject and including a first plurality of data points, each data point of the first plurality of data points being associated with a position of a portion of the first physical subject. Within the virtual environment, a first skeletal mesh can be generated and positioned at a first initial position relative to the at least one digital object. Each of the first plurality of data points can be associated with a corresponding point along the skeletal mesh. Positional information of the first skeletal mesh and the at least one digital object can be streamed to a client device.

Abstract: Systems and methods of the present disclosure include interactive editing for generated three-dimensional (3D) models, such as those represented by neural radiance fields (NeRFs). A 3D model may be presented to a user in which the user may identify one or more localized regions for editing and/or modification. The localized regions may be selected and a corresponding 3D volume for that region may be provided to one or more generative networks, along with a prompt, to generate new content for the localized regions. Each of the original NeRF and the newly generated NeRF for the new content may then be combined into a single NeRF for a combined 3D representation with the original content and the localized modifications.

Abstract: A text-to-3D machine learning (ML) model is trained by rendering a pre-existing 3D model along with an associated depth map using plural camera settings and rendering a neural radiance field (NeRF) along with an associated depth map using the plural camera settings used in rendering the 3D model. A composite is established from the depth maps, which is used to train the ML model.

Abstract: In a method, a longitudinal angle, an azimuthal angle, illumination information, and color information of a pixel in a hair area of a virtual image corresponding to each optical path of a virtual main light source are obtained. For each optical path of the virtual main light source, a respective longitudinal scattering amount is determined based on the longitudinal angle and the illumination information of the pixel, a respective azimuthal scattering amount is determined based on the azimuthal angle of the pixel, and a respective scattering amount of the pixel corresponding to the respective optical path is determined according to the longitudinal scattering amount, the azimuthal scattering amount, and the color information of the pixel. Scattering amounts of the pixel corresponding to the optical paths of the virtual main light source are fused to obtain first coloring information of the pixel corresponding to the virtual main light source.

Abstract: When preparing and storing a primitive list in a tile-based graphics processing system, a first block of memory space is allocated for storing the primitive list. When there is insufficient space in the first block of memory space to store all of the graphics primitives for the primitive list, a next block of memory space to be used for storing the primitive list is allocated for storing the primitive list. An indication of the location in memory of the allocated next block of memory space is written at the beginning of the first block of memory space.

Abstract: Methods, device, system and one or more computer readable media having one or more computer programs with instructions to generate custom-fit garment patterns from a 3D body scan are disclosed. The patterns may be obtained by unwrapping the 3D body scan (3D image) into 2D using defined datapoints associated with the surface of a body in a target region. Patterns may be generated for different types of garments. The custom-fit garment patterns generated from the 3D body scan may be basic patterns, which may be further customized or modified as desired.

Abstract: Vector format based computer graphics tools have become very powerful tools allowing artists, designers etc. to mimic many artistic styles, exploit automated techniques, etc. and across different simulated physical media and digital media. However, hand-drawing and sketching in vector format graphics is unnatural and a user's strokes rendered by software are generally unnatural and appear artificial. In contrast to today's hand-drawing and sketching which requires significant training of and understanding by the user of complex vector graphics methods embodiments of the invention lower the barrier to accessing computer graphics applications for users in respect of making hand-drawing or sketching easier to perform. Accordingly, the inventors have established a direct vector-based hand-drawing/sketching entry format supporting any input methodology.

Abstract: An image rendering method includes: acquiring a project scene, materials of an object in the project scene including a light source material, and the light source material being a material that is endowed with a light source attribute by setting a corresponding shading model to be a custom grid light source shading model; searching object grids with the light source material from the project scene, and performing light source structure conversion on the object grids with the light source material to obtain light source grids, the object grids being grids used for forming the object in the project scene; and using each of the light source grids as a light source, to perform direct illumination rendering on each of pixels of the image representing the project scene, and fusing a direct illumination rendering result of each of the light source grids for each of the pixels to obtain a rendered target image.

Abstract: A three dimensional image generation method can include capturing a plurality of images of an object, generating a plurality of point clouds corresponding to a first sequence and a plurality pieces of first pose information according to the plurality of images, generating a second sequence according to a plurality of correlations among the plurality of images, performing a plurality of registration operations on the plurality of point clouds in the second sequence to adjust the plurality pieces of first pose information to generate a plurality pieces of second pose information, and combining the plurality of point clouds according to the plurality pieces of second pose information to generate a three dimensional image of the object.

Abstract: An electronic device may include an electronic display having multiple display pixels that display an image based on dithered image data. The electronic device may also include image processing circuitry that generates the dithered image data based on input image data and a threshold gray level that is greater than one. Generating the dithered image data may include replacing each gray level of the input image data that is less than the threshold gray level with either a zero gray level or the threshold gray level according to a dither pattern.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, including: receiving, by a shape modeling computer program, a selection of first geometry defined in a data structure used by the computer program to represent a three-dimensional model of an object and an indication of an amount of complexity reduction, The computer program produces a second geometry defined in the data structure based on the indication of the amount of indicated complexity reduction and taking into account local shape curvature for the first geometry, where the second geometry replaces the first geometry in representing the three-dimensional model of the object. The computer program provides the three-dimensional model of the object, with the second geometry included in the three-dimensional model, for use in manufacturing a physical structure corresponding to the object using one or more computer-controlled manufacturing systems, or for use in displaying the object on a display screen.

Abstract: Disclosed is a system capable of synthesizing (encoding) two images taken by two left and right cameras into a 3D video, and viewing the 3D image on a display. The system comprises a computer that uses two cameras with a resolution equivalent to half the number of horizontal pixels of a 3D display, to execute an application program, and arrange each pixel of the two cameras on pixels equivalent to the display. The checkered pattern configuration means that the pixels of the first scan line of the left camera are configured sequentially by skipping one position on the first scan line (odd-numbered rows) of the display, that is, only configured in odd-numbered columns; the pixels of the first scanning line of the right camera skip one position from the second column on the second scanning line (even-numbered row) of the display, that is, only configured in even-numbered.

Abstract: Certain aspects and features of the present disclosure relate to receiving an input corresponding to a fill for a vector graphical representation including an overlapping area. Aspects and features further involve converting the vector graphical representation to a simple graph, and aligning contours within the simple graph to provide a unified winding number for the overlapping area. Aspects and features also involve rendering the vector graphical representation with the fill using the simple graph to include the overlapping area within the rendered representation as filled.

Abstract: In accordance with the described techniques, an image transformation system receives an input image and a text prompt, and leverages a generator network to edit the input image based on the text prompt. The generator network includes a plurality of layers configured to perform respective edits. A plurality of masks are generated based on the text prompt that define local edit regions, respectively, of the input image for respective layers of the generator network. Further, the generator network generates an edited image by editing the input image based on the plurality of masks, the respective edits of the respective layers, and the text prompt.

Abstract: A reconstruction method of a three dimensional (3D) model and a computing apparatus are provided. In the method, multiple structures in the 3D model are determined. An object in the 3D model is separated from an original location to form a hollow. The hollow is adjacent to at least two neighboring structures among the structures. The neighboring structures are respectively extended to cover the hollow. A similarity of an extended part covering the hollow is determined. The similarity is a compared result of an adjacent structure of the extended part. A target structure of the hollow is determined according to the similarity. The target structure is used for compensating the hollow.

Abstract: Systems and methods are provided for enhanced animation generation based on generative modeling. An example method includes training models based on faces and information associated with persons. The modeling system being trained to reconstruct expressions, textures, and models of persons.

Abstract: Systems and methods implement a technique for altering the shape of the cells by shifting coordinates of points along cell boundaries using a set of periodic functions. To avoid having cell boundaries along the scene surfaces, wavelengths of those periodic functions are selected so they are not a multiple of an original discretization. The coordinates may be shifted along different axes of the cells and may generate different cells having a variety of different outlines to reduce a likelihood of a cell boundary being positioned along a scene boundary.