公开(公告)号：US11836851B2

公开(公告)日：2023-12-05

申请号：US17589620

申请日：2022-01-31

申请人： Electronic Arts Inc.

发明人： Binh Huy Le ,  John Peter Lewis

IPC分类号： G06T15/60 ,  G06T15/06 ,  G06T13/40 ,  G06T15/10 ,  A63F13/52 ,  G06N20/00 ,  G06T15/50

CPC分类号： G06T15/60 ,  A63F13/52 ,  G06N20/00 ,  G06T13/40 ,  G06T15/06 ,  G06T15/10 ,  G06T15/506 ,  A63F2300/6607 ,  A63F2300/6646

摘要： Systems and methods are disclosed for calculating dynamic ambient occlusion (AO) values for character models to yield high-quality approximations of global illumination effects. The approach utilizes a dual component machine-learning model that factorizes dynamic AO computation into a non-linear component, in which visibility is determined by approximating spheres and their casted shadows, and a linear component that leverages a skinning-like algorithm for efficiency. The parameters of both components are trained in a regression against ground-truth AO values. The resulting model accommodates lighting interactions with external objects and can be generalized without requiring carefully constructed training data.

公开(公告)号：US11830129B2

公开(公告)日：2023-11-28

申请号：US17385462

申请日：2021-07-26

申请人： Snap Inc.

发明人： Yuriy Volkov ,  Egor Nemchinov ,  Gleb Dmukhin

IPC分类号： G06T5/50 ,  G06T7/73 ,  G06T19/20 ,  G06T15/50

CPC分类号： G06T15/503 ,  G06T7/75 ,  G06T15/506 ,  G06T19/20 ,  G06T2200/24 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2219/2012

摘要： A messaging system performs image processing to relight objects with neural networks for images provided by users of the messaging system. A method of relighting objects with neural networks includes receiving an input image with first lighting properties comprising an object with second lighting properties and processing the input image using a convolutional neural network to generate an output image with the first lighting properties and comprising the object with third lighting properties, where the convolutional neural network is trained to modify the second lighting properties to be consistent with lighting conditions indicated by the first lighting properties to generate the third lighting properties. The method further includes modifying the second lighting properties of the object to generate the object with modified second lighting properties and blending the third lighting properties with the modified second lighting properties to generate a modified output image comprising the object with fourth lighting properties.

公开(公告)号：US11823326B2

公开(公告)日：2023-11-21

申请号：US18317067

申请日：2023-05-13

申请人： CONTEMPORARY AMPEREX TECHNOLOGY CO., LIMITED

发明人： Guannan Jiang ,  Lili Han

IPC分类号： G06T7/00 ,  G06T7/55 ,  G06T15/50 ,  G06T19/20

CPC分类号： G06T15/506 ,  G06T7/55 ,  G06T19/20 ,  G06T2207/10028 ,  G06T2219/2012

摘要： An image processing method includes obtaining two-dimensional and three-dimensional images of an object, extracting luminance and depth information from the three-dimensional image to generate luminance and depth image for the object, graying the two-dimensional image to obtain a single-channel grayscale image, selecting at least three same-location points from each of the grayscale and luminance image, calculating a coordinate transformation matrix between the grayscale and luminance images based on coordinates of the at least three same-location points in each of the grayscale and luminance images, and aligning the two-dimensional image with the luminance and depth images based on the coordinate transformation matrix to obtain fused image data. The fused image data includes color information of the two-dimensional image and the luminance and depth information of the three-dimensional image.

公开(公告)号：US20230368437A1

公开(公告)日：2023-11-16

申请号：US18359647

申请日：2023-07-26

申请人： LUXION, INC.

发明人： Zahra Montazeri ,  Søren Gammelmark ,  Shuang Zhao ,  Henrik Wann Jensen

IPC分类号： G06T11/00 ,  G06T15/50 ,  G06F30/30 ,  G06T19/20 ,  G06F113/12

CPC分类号： G06T11/001 ,  G06T15/50 ,  G06F30/30 ,  G06T19/20 ,  G06T2210/16 ,  G06F2113/12 ,  G06T2200/24

摘要： Systems and methods configured to determine appearance of woven and knitted textiles at the ply-level are presented herein. Exemplary embodiments may: obtain an input pattern of a textile, the input pattern comprising a two-dimensional weave pattern; obtain appearance information, the appearance information including one or more of color, transparency, or roughness; determine ply curve geometry based on ply-level fiber details making up individual plys; generate an image simulating an appearance of the textile based on the two-dimensional weave pattern, the appearance information, and the ply curve geometry so that the image simulating the appearance of the textile takes into account the ply-level fiber details; and/or perform other operations.

公开(公告)号：US11816781B2

公开(公告)日：2023-11-14

申请号：US17354906

申请日：2021-06-22

申请人： ADVANCED MICRO DEVICES, INC.

发明人： Guillaume Marie Boisse

IPC分类号： G06T15/06 ,  G06T15/50

CPC分类号： G06T15/06 ,  G06T15/50

摘要： A processor shares path tracing data across sampling locations to amortize computations across space and time. The processor maps a group of sampling locations of a frame that are adjacent to each other in world-space to a cell of a hash table. Each cell of the hash table stores a list of reservoirs that are each associated with a ray that intersects the group of sampling locations from world-space. The processor resamples the reservoirs at the hash table by combining and re-using reservoirs across neighboring sampling locations and corresponding sampling locations of the previous frame to select a set of samples mapped to the cell. The processor then performs resampling of the selected set of samples to obtain a representative light sample to determine a value for the cell and renders the frame based on the value of the cell.

公开(公告)号：US11816404B2

公开(公告)日：2023-11-14

申请号：US17083787

申请日：2020-10-29

申请人： NVIDIA Corporation

发明人： Thomas Müller ,  Fabrice Pierre Armand Rousselle ,  Alexander Georg Keller ,  Jan Novák

IPC分类号： G06F30/27 ,  G06T15/06 ,  G06F17/11 ,  G06T15/50 ,  G06N3/045 ,  G06F111/10

CPC分类号： G06F30/27 ,  G06F17/11 ,  G06N3/045 ,  G06T15/06 ,  G06T15/506 ,  G06F2111/10

摘要： Monte Carlo and quasi-Monte Carlo integration are simple numerical recipes for solving complicated integration problems, such as valuating financial derivatives or synthesizing photorealistic images by light transport simulation. A drawback of a straightforward application of (quasi-)Monte Carlo integration is the relatively slow convergence rate that manifests as high error of Monte Carlo estimators. Neural control variates may be used to reduce error in parametric (quasi-)Monte Carlo integration—providing more accurate solutions in less time. A neural network system has sufficient approximation power for estimating integrals and is efficient to evaluate. The efficiency results from the use of a first neural network that infers the integral of the control variate and using normalizing flows to model a shape of the control variate.

公开(公告)号：US20230360320A1

公开(公告)日：2023-11-09

申请号：US18354619

申请日：2023-07-18

申请人： Adobe Inc.

发明人： Ruben Villegas ,  Yunseok Jang ,  Duygu Ceylan Aksit ,  Jimei Yang ,  Xin Sun

IPC分类号： G06T15/50 ,  G06T7/70 ,  G06T15/06 ,  G06N3/04 ,  G06T15/04 ,  G06T15/20

CPC分类号： G06T15/506 ,  G06T7/70 ,  G06T15/06 ,  G06N3/04 ,  G06T15/04 ,  G06T15/20

摘要： This disclosure describes methods, non-transitory computer readable storage media, and systems that generate realistic shading for three-dimensional objects inserted into digital images. The disclosed system utilizes a light encoder neural network to generate a representation embedding of lighting in a digital image. Additionally, the disclosed system determines points of the three-dimensional object visible within a camera view. The disclosed system generates a self-occlusion map for the digital three-dimensional object by determining whether fixed sets of rays uniformly sampled from the points intersects with the digital three-dimensional object. The disclosed system utilizes a generator neural network to determine a shading map for the digital three-dimensional object based on the representation embedding of lighting in the digital image and the self-occlusion map. Additionally, the disclosed system generates a modified digital image with the three-dimensional object inserted into the digital image with consistent lighting of the three-dimensional object and the digital image.

公开(公告)号：US11809487B2

公开(公告)日：2023-11-07

申请号：US17320648

申请日：2021-05-14

申请人： Google LLC

发明人： Janne Matias Kontkanen

IPC分类号： G06T17/00 ,  G06V20/30 ,  G06F16/583 ,  G06T15/50 ,  G06T15/00 ,  G06T15/20 ,  G06T15/04

CPC分类号： G06F16/5838 ,  G06T15/00 ,  G06T15/04 ,  G06T15/20 ,  G06T15/205 ,  G06T15/503 ,  G06T17/00 ,  G06V20/30

摘要： A system and method is provided for displaying surfaces of an object from a vantage point different from the vantage point from which imagery of the object was captured. In some aspects, imagery may be generated for display by combining visual characteristics from multiple source images and applying greater weight to the visual characteristics of some of the source images relative to the other source images. The weight may be based on the orientation of the surface relative to the location from which the image was captured and the location from which the object will be displayed.

公开(公告)号：US11804011B2

公开(公告)日：2023-10-31

申请号：US17447804

申请日：2021-09-15

申请人： LlamaZOO Interactive Inc.

发明人： Charles Lavigne ,  Li Jl

IPC分类号： G06T19/00 ,  G06T17/20 ,  G06T15/08 ,  G06T1/20 ,  G06T15/00 ,  G06T15/20 ,  G06T15/50

CPC分类号： G06T19/00 ,  G06T1/20 ,  G06T15/005 ,  G06T15/08 ,  G06T15/20 ,  G06T15/503 ,  G06T17/20 ,  G06T2200/24

摘要： Disclosed is a method and apparatus for enabling interactive visualization of three-dimensional volumetric models. The method involves maintaining three-dimensional volumetric models represented by explicit surfaces. In accordance with an embodiment of the disclosure, the method also involves, for a current point of view, generating and displaying images of the volumetric models in a manner that clarifies internal structures by accounting for light attenuation inside the volumetric models as a function of spatial positions of the explicit surfaces. The method also involves, upon receiving user input that adjusts a display variable, repeating the generating and the displaying of the images in accordance with the display variable that has been adjusted, thereby enabling interactive visualization of the volumetric models while simultaneously clarifying the internal structures by accounting for the light attenuation inside the volumetric models.

公开(公告)号：US11804007B2

公开(公告)日：2023-10-31

申请号：US17218920

申请日：2021-03-31

申请人： Disney Enterprises, Inc.

发明人： Dane M. Coffey ,  Siroberto Scerbo ,  Evan M. Goldberg ,  Christopher Richard Schroers ,  Daniel L Baker ,  Mark R. Mine ,  Erika Varis Doggett

IPC分类号： G06T15/20 ,  G06T15/04 ,  G06T15/50 ,  G06T17/20 ,  H04N13/275 ,  H04N13/282

CPC分类号： G06T15/205 ,  G06T15/04 ,  G06T15/50 ,  G06T17/20 ,  H04N13/275 ,  H04N13/282

摘要： An image processing system includes a computing platform having processing hardware, a display, and a system memory storing a software code. The processing hardware is configured to execute the software code to receive a three-dimensional (3D) digital model, surround the 3D digital model with multiple virtual cameras oriented toward the 3D digital model, and generate, using the virtual cameras, a multiple renders of the 3D digital model. The processing hardware is further configured to execute the software code to generate a UV texture coordinate space for a surface projection of the 3D digital model, and to transfer, using the multiple renders, lighting color values for each of multiple surface portions of the 3D digital model to the UV texture coordinate space.