公开(公告)号：US20200312009A1

公开(公告)日：2020-10-01

申请号：US16368548

申请日：2019-03-28

Applicant: ADOBE INC.

Inventor： Xin Sun ,  Nathan Aaron Carr ,  Alexandr Kuznetsov

IPC: G06T15/06 ,  G06T15/00 ,  G06N3/08 ,  G06N20/00 ,  G06N7/00

Abstract: Images are rendered from deeply learned raytracing parameters. Active learning, via a machine learning (ML) model (e.g., implemented by a deep neural network), is used to automatically determine, infer, and/or predict optimized, or at least somewhat optimized, values for parameters used in raytracing methods. Utilizing deep learning to determine optimized, or at least somewhat optimized, values for raytracing parameters is in contrast to conventional methods, which require users to rely of heuristics for parameter value setting. In various embodiments, one or more parameters regarding the termination and splitting of traced light paths in stochastic-based (e.g., Monte Carlo) raytracing are determined via active learning. In some embodiments, one or more parameters regarding the sampling rate of shadow rays are also determined.

公开(公告)号：US11816779B2

公开(公告)日：2023-11-14

申请号：US17538311

申请日：2021-11-30

Applicant: Adobe Inc. ,  The Regents of the University of California

Inventor： Krishna Bhargava Mullia Lakshminarayana ,  Zexiang Xu ,  Milos Hasan ,  Ravi Ramamoorthi ,  Alexandr Kuznetsov

IPC: G06T15/04 ,  G06T15/55 ,  G06N3/045

CPC classification number: G06T15/04 ,  G06N3/045 ,  G06T15/55

Abstract: Methods and systems disclosed herein relate generally to surface-rendering neural networks to represent and render a variety of material appearances (e.g., textured surfaces) at different scales. The system includes receiving image metadata for a texel that includes position, incoming and outgoing radiance direction, and a kernel size. The system applies a offset-prediction neural network to the query to identify an offset coordinate for the texel. The system inputs the offset coordinate to a data structure to determine a feature vector for the texel of the textured surface. The reflectance feature vector is then processed using a decoder neural network to estimate a light-reflectance value of the texel, at which the light-reflectance value is used to render the texel of the textured surface.

公开(公告)号：US20240169653A1

公开(公告)日：2024-05-23

申请号：US17993854

申请日：2022-11-23

Applicant: Adobe Inc. ,  The Regents of the University of California

Inventor： Krishna Bhargava Mullia Lakshminarayana ,  Zexiang Xu ,  Milos Hasan ,  Fujun Luan ,  Alexandr Kuznetsov ,  Xuezheng Wang ,  Ravi Ramamoorthi

IPC: G06T15/06 ,  G06T15/04 ,  G06T15/50

CPC classification number: G06T15/06 ,  G06T15/04 ,  G06T15/506 ,  G06T2215/12

Abstract: A scene modeling system accesses a three-dimensional (3D) scene including a 3D object. The scene modeling system applies a silhouette bidirectional texture function (SBTF) model to the 3D object to generate an output image of a textured material rendered as a surface of the 3D object. Applying the SBTF model includes determining a bounding geometry for the surface of the 3D object. Applying the SBTF model includes determining, for each pixel of the output image, a pixel value based on the bounding geometry. The scene modeling system displays, via a user interface, the output image based on the determined pixel values.

公开(公告)号：US20230169715A1

公开(公告)日：2023-06-01

申请号：US17538311

申请日：2021-11-30

Applicant: Adobe Inc. ,  Regents of the University of California

Inventor： Krishna Bhargava Mullia Lakshminarayana ,  Zexiang Xu ,  Milos Hasan ,  Ravi Ramamoorthi ,  Alexandr Kuznetsov

IPC: G06T15/04 ,  G06T15/55 ,  G06N3/04

CPC classification number: G06T15/04 ,  G06T15/55 ,  G06N3/0454

Abstract: Methods and systems disclosed herein relate generally to surface-rendering neural networks to represent and render a variety of material appearances (e.g., textured surfaces) at different scales. The system includes receiving image metadata for a texel that includes position, incoming and outgoing radiance direction, and a kernel size. The system applies a offset-prediction neural network to the query to identify an offset coordinate for the texel. The system inputs the offset coordinate to a data structure to determine a feature vector for the texel of the textured surface. The reflectance feature vector is then processed using a decoder neural network to estimate a light-reflectance value of the texel, at which the light-reflectance value is used to render the texel of the textured surface.

公开(公告)号：US10902665B2

公开(公告)日：2021-01-26

申请号：US16368548

申请日：2019-03-28

Applicant: ADOBE INC.

Inventor： Xin Sun ,  Nathan Aaron Carr ,  Alexandr Kuznetsov

IPC: G06T15/06 ,  G06T15/00 ,  G06N7/00 ,  G06N20/00 ,  G06N3/08

Abstract: Images are rendered from deeply learned raytracing parameters. Active learning, via a machine learning (ML) model (e.g., implemented by a deep neural network), is used to automatically determine, infer, and/or predict optimized, or at least somewhat optimized, values for parameters used in raytracing methods. Utilizing deep learning to determine optimized, or at least somewhat optimized, values for raytracing parameters is in contrast to conventional methods, which require users to rely of heuristics for parameter value setting. In various embodiments, one or more parameters regarding the termination and splitting of traced light paths in stochastic-based (e.g., Monte Carlo) raytracing are determined via active learning. In some embodiments, one or more parameters regarding the sampling rate of shadow rays are also determined.