公开(公告)号：US20230274492A1

公开(公告)日：2023-08-31

申请号：US18149454

申请日：2023-01-03

Applicant: Nvidia Corporation

Inventor： Zhiqin Chen ,  Kangxue Yin ,  Sanja Fidler

IPC: G06T15/04 ,  G06T7/40

CPC classification number: G06T15/04 ,  G06T7/40 ,  G06T2210/56 ,  G06T2207/10028 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/20084

Abstract: Approaches presented herein can utilize a network that learns to embed three-dimensional (3D) coordinates on a surface of one or more 3D shapes into an aligned two-dimensional (2D) texture space, where corresponding parts of different 3D shapes can be mapped to the same location in a texture image. Alignment can be performed using a texture alignment module that generates a set of basis images for synthesizing textures. A trained network can generate a basis shared by all shape textures, and can predict input-specific coefficients to construct the output texture for each shape as a linear combination of the basis images, then deform the texture to match the pose of the input. Such an approach can ensure alignment of textures, even in situations with at least somewhat limited network capacity. To unwrap shapes of complex structure or topology, a masking network can be utilized that cuts the shape into multiple pieces to reduce the distortion in the 2D mapping.

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：US11335056B1

公开(公告)日：2022-05-17

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

IPC: G06T15/08 ,  G06T17/00

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.