公开(公告)号：US20230134690A1

公开(公告)日：2023-05-04

申请号：US17981770

申请日：2022-11-07

Applicant: Nvidia Corporation

Inventor： Wenzheng Chen ,  Yuxuan Zhang ,  Sanja Fidler ,  Huan Ling ,  Jun Gao ,  Antonio Torralba Barriuso

IPC: G06T17/00 ,  G06N3/088 ,  G06T15/10 ,  G06N3/045

Abstract: Approaches are presented for training an inverse graphics network. An image synthesis network can generate training data for an inverse graphics network. In turn, the inverse graphics network can teach the synthesis network about the physical three-dimensional (3D) controls. Such an approach can provide for accurate 3D reconstruction of objects from 2D images using the trained inverse graphics network, while requiring little annotation of the provided training data. Such an approach can extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers, enabling a disentangled generative model to function as a controllable 3D “neural renderer,” complementing traditional graphics renderers.

公开(公告)号：US11922558B2

公开(公告)日：2024-03-05

申请号：US17826611

申请日：2022-05-27

Applicant: NVIDIA Corporation

Inventor： Wenzheng Chen ,  Joey Litalien ,  Jun Gao ,  Zian Wang ,  Clement Tse Tsian Christophe Louis Fuji Tsang ,  Sameh Khamis ,  Or Litany ,  Sanja Fidler

IPC: G06T15/06 ,  G06T15/50 ,  G06T19/20

CPC classification number: G06T15/06 ,  G06T15/506 ,  G06T19/20 ,  G06T2219/2012

Abstract: In various examples, information may be received for a 3D model, such as 3D geometry information, lighting information, and material information. A machine learning model may be trained to disentangle the 3D geometry information, the lighting information, and/or material information from input data to provide the information, which may be used to project geometry of the 3D model onto an image plane to generate a mapping between pixels and portions of the 3D model. Rasterization may then use the mapping to determine which pixels are covered and in what manner, by the geometry. The mapping may also be used to compute radiance for points corresponding to the one or more 3D models using light transport simulation. Disclosed approaches may be used in various applications, such as image editing, 3D model editing, synthetic data generation, and/or data set augmentation.

公开(公告)号：US11494976B2

公开(公告)日：2022-11-08

申请号：US17193405

申请日：2021-03-05

Applicant: Nvidia Corporation

Inventor： Wenzheng Chen ,  Yuxuan Zhang ,  Sanja Fidler ,  Huan Ling ,  Jun Gao ,  Antonio Torralba Barriuso

IPC: G06T17/00 ,  G06N3/04 ,  G06N3/08 ,  G06T15/10

Abstract: Approaches are presented for training an inverse graphics network. An image synthesis network can generate training data for an inverse graphics network. In turn, the inverse graphics network can teach the synthesis network about the physical three-dimensional (3D) controls. Such an approach can provide for accurate 3D reconstruction of objects from 2D images using the trained inverse graphics network, while requiring little annotation of the provided training data. Such an approach can extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers, enabling a disentangled generative model to function as a controllable 3D “neural renderer,” complementing traditional graphics renderers.