-
公开(公告)号：US12112445B2
公开(公告)日：2024-10-08
申请号：US17467792
申请日：2021-09-07
Applicant: Nvidia Corporation
Inventor： Kangxue Yin , Jun Gao , Masha Shugrina , Sameh Khamis , Sanja Fidler
CPC classification number: G06T19/20 , G06N3/045 , G06T3/02 , G06T3/18 , G06T7/11 , G06T15/04 , G06T17/20 , G06T2200/04 , G06T2207/20084 , G06T2219/2021
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：US20220392162A1
公开(公告)日：2022-12-08
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
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：US20240212261A1
公开(公告)日：2024-06-27
申请号：US18412228
申请日：2024-01-12
Applicant: Nvidia Corporation
Inventor： Towaki Alan Takikawa , Joey Litalien , Kangxue Yin , Karsten Julian Kreis , Charles Loop , Morgan McGuire , Sanja Fidler
CPC classification number: G06T15/08 , G06T15/005 , G06T17/005 , G06T2210/36
Abstract: Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MHLPs) can be used with an octree-based feature representation for the learned neural SDFs.
-
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
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：US20220172423A1
公开(公告)日：2022-06-02
申请号：US17314182
申请日：2021-05-07
Applicant: Nvidia Corporation
Inventor： Towaki Alan Takikawa , Joey Litalien , Kangxue Yin , Karsten Julian Kreis , Charles Loop , Morgan McGuire , Sanja Fidler
Abstract: Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MLPs) can be used with an octree-based feature representation for the learned neural SDFs.
-
Patent Agency Ranking
公开(公告)号：US20240296627A1
公开(公告)日：2024-09-05
申请号：US18662020
申请日：2024-05-13
Applicant: NVIDIA Corporation
Inventor： Tianchang Shen , Jun Gao , Kangxue Yin , Ming-Yu Liu , Sanja Fidler
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：US20240290054A1
公开(公告)日：2024-08-29
申请号：US18174863
申请日：2023-02-27
Applicant: Nvidia Corporation
Inventor： Kangxue Yin , Huan Ling , Masha Shugrina , Sameh Khamis , Sanja Fidler
IPC: G06T19/20 , G06N3/0475 , G06N3/08 , G06T15/04 , G06T15/10
CPC classification number: G06T19/20 , G06N3/0475 , G06N3/08 , G06T15/04 , G06T15/10 , G06T2219/2021 , G06T2219/2024
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 combined with a generative network to generate objects based on parameters associated with a textual input. An input including a 3D mesh and texture may be provided to a trained system along with a textual input that includes parameters for object generation. Features of the input object may be identified and then tuned in accordance with the textual input to generate a modified 3D object that includes a new texture along with one or more geometric adjustments.
-
公开(公告)号：US20220284659A1
公开(公告)日：2022-09-08
申请号：US17745478
申请日：2022-05-16
Applicant: Nvidia Corporation
Inventor： Towaki Alan Takikawa , Joey Litalien , Kangxue Yin , Karsten Julian Kreis , Charles Loop , Morgan McGuire , Sanja Fidler
Abstract: Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MLPs) can be used with an octree-based feature representation for the learned neural SDFs.
-
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
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：US11875449B2
公开(公告)日：2024-01-16
申请号：US17745478
申请日：2022-05-16
Applicant: Nvidia Corporation
Inventor： Towaki Alan Takikawa , Joey Litalien , Kangxue Yin , Karsten Julian Kreis , Charles Loop , Morgan McGuire , Sanja Fidler
CPC classification number: G06T15/08 , G06T17/005 , G06T2210/36
Abstract: Systems and methods are described for rendering complex surfaces or geometry. In at least one embodiment, neural signed distance functions (SDFs) can be used that efficiently capture multiple levels of detail (LODs), and that can be used to reconstruct multi-dimensional geometry or surfaces with high image quality. An example architecture can represent complex shapes in a compressed format with high visual fidelity, and can generalize across different geometries from a single learned example. Extremely small multi-layer perceptrons (MLPs) can be used with an octree-based feature representation for the learned neural SDFs.
-
-
-
-
-
-
-
-
-
Search Results
13
records
(took 0.013 seconds)
