公开(公告)号：US20240096017A1

公开(公告)日：2024-03-21

申请号：US17895793

申请日：2022-08-25

Applicant: Nvidia Corporation

Inventor： Jun Gao ,  Tianchang Shen ,  Zan Gojcic ,  Wenzheng Chen ,  Zian Wang ,  Daiqing Li ,  Or Litany ,  Sanja Fidler

IPC: G06T17/20

CPC classification number: G06T17/20 ,  G06T2207/10024 ,  G06T2207/20084

Abstract: Apparatuses, systems, and techniques are presented to generate digital content. In at least one embodiment, one or more neural networks are used to generate one or more textured three-dimensional meshes corresponding to one or more objects based, at least in part, one or more two-dimensional images of the one or more objects.

公开(公告)号：US20220383582A1

公开(公告)日：2022-12-01

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 ,  G06T19/20 ,  G06T15/50

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：US20220083807A1

公开(公告)日：2022-03-17

申请号：US17020649

申请日：2020-09-14

Applicant: NVIDIA Corporation

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

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: Apparatuses, systems, and techniques to determine pixel-level labels of a synthetic image. In at least one embodiment, the synthetic image is generated by one or more generative networks and the pixel-level labels are generated using a combination of data output by a plurality of layers of the generative networks.

公开(公告)号：US20250029351A1

公开(公告)日：2025-01-23

申请号：US18905841

申请日：2024-10-03

Applicant: Nvidia Corporation

Inventor： Kangxue Yin ,  Jun Gao ,  Masha Shugrina ,  Sameh Khamis ,  Sanja Fidler

IPC: G06T19/20 ,  G06N3/045 ,  G06T3/02 ,  G06T3/18 ,  G06T7/11 ,  G06T15/04 ,  G06T17/20

Abstract: Generation of three-dimensional (3D) object models may be challenging for users without a sufficient skill set for content creation and may also be resource intensive. One or more style transfer networks may be used for part-aware style transformation of both geometric features and textural components of a source asset to a target asset. The source asset may be segmented into particular parts and then ellipsoid approximations may be warped according to correspondence of the particular parts to the target assets. Moreover, a texture associated with the target asset may be used to warp or adjust a source texture, where the new texture can be applied to the warped parts.

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：US20230074420A1

公开(公告)日：2023-03-09

申请号：US17467792

申请日：2021-09-07

Applicant: Nvidia Corporation

Inventor： Kangxue Yin ,  Jun Gao ,  Masha Shugrina ,  Sameh Khamis ,  Sanja Fidler

IPC: G06T19/20 ,  G06T15/04 ,  G06T17/20 ,  G06T7/11 ,  G06T3/00 ,  G06N3/04

Abstract: Generation of three-dimensional (3D) object models may be challenging for users without a sufficient skill set for content creation and may also be resource intensive. One or more style transfer networks may be used for part-aware style transformation of both geometric features and textural components of a source asset to a target asset. The source asset may be segmented into particular parts and then ellipsoid approximations may be warped according to correspondence of the particular parts to the target assets. Moreover, a texture associated with the target asset may be used to warp or adjust a source texture, where the new texture can be applied to the warped parts.

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.

公开(公告)号：US20240185506A1

公开(公告)日：2024-06-06

申请号：US18441486

申请日：2024-02-14

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：US11983815B2

公开(公告)日：2024-05-14

申请号：US17718172

申请日：2022-04-11

Applicant: NVIDIA Corporation

Inventor： Tianchang Shen ,  Jun Gao ,  Kangxue Yin ,  Ming-Yu Liu ,  Sanja Fidler

IPC: G06T17/20 ,  G06T7/50

CPC classification number: G06T17/20 ,  G06T7/50 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: In various examples, a deep three-dimensional (3D) conditional generative model is implemented that can synthesize high resolution 3D shapes using simple guides—such as coarse voxels, point clouds, etc.—by marrying implicit and explicit 3D representations into a hybrid 3D representation. The present approach may directly optimize for the reconstructed surface, allowing for the synthesis of finer geometric details with fewer artifacts. The systems and methods described herein may use a deformable tetrahedral grid that encodes a discretized signed distance function (SDF) and a differentiable marching tetrahedral layer that converts the implicit SDF representation to an explicit surface mesh representation. This combination allows joint optimization of the surface geometry and topology as well as generation of the hierarchy of subdivisions using reconstruction and adversarial losses defined explicitly on the surface mesh.

公开(公告)号：US20230140460A1

公开(公告)日：2023-05-04

申请号：US17827918

申请日：2022-05-30

Applicant: NVIDIA Corporation

Inventor： Carl Jacob Munkberg ,  Jon Niklas Theodor Hasselgren ,  Tianchang Shen ,  Jun Gao ,  Wenzheng Chen ,  Alex John Bauld Evans ,  Thomas Müller-Höhne ,  Sanja Fidler

IPC: G06T17/20 ,  G06T15/50 ,  G06T9/00 ,  G06T15/04 ,  G06N3/08

Abstract: A technique is described for extracting or constructing a three-dimensional (3D) model from multiple two-dimensional (2D) images. In an embodiment, a foreground segmentation mask or depth field may be provided as an additional supervision input with each 2D image. In an embodiment, the foreground segmentation mask or depth field is automatically generated for each 2D image. The constructed 3D model comprises a triangular mesh topology, materials, and environment lighting. The constructed 3D model is represented in a format that can be directly edited and/or rendered by conventional application programs, such as digital content creation (DCC) tools. For example, the constructed 3D model may be represented as a triangular surface mesh (with arbitrary topology), a set of 2D textures representing spatially-varying material parameters, and an environment map. Furthermore, the constructed 3D model may be included in 3D scenes and interacts realistically with other objects.