-
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：US20230281847A1
公开(公告)日：2023-09-07
申请号：US17592096
申请日：2022-02-03
Applicant: NVIDIA Corporation
Inventor： Yiran Zhong , Charles Loop , Nikolai Smolyanskiy , Ke Chen , Stan Birchfield , Alexander Popov
CPC classification number: G06T7/55 , G06T7/70 , G06V10/462 , G06T2207/20081 , G06T2207/30252
Abstract: In various examples, methods and systems are provided for estimating depth values for images (e.g., from a monocular sequence). Disclosed approaches may define a search space of potential pixel matches between two images using one or more depth hypothesis planes based at least on a camera pose associated with one or more cameras used to generate the images. A machine learning model(s) may use this search space to predict likelihoods of correspondence between one or more pixels in the images. The predicted likelihoods may be used to compute depth values for one or more of the images. The predicted depth values may be transmitted and used by a machine to perform one or more operations.
-
公开(公告)号：US20210326694A1
公开(公告)日：2021-10-21
申请号：US16852944
申请日：2020-04-20
Applicant: Nvidia Corporation
Inventor： Jialiang Wang , Varun Jampani , Stan Birchfield , Charles Loop , Jan Kautz
Abstract: Apparatuses, systems, and techniques are presented to determine distance for one or more objects. In at least one embodiment, a disparity network is trained to determine distance data from input stereoscopic images using a loss function that includes at least one of a gradient loss term and an occlusion loss term.
-
公开(公告)号：US20240257443A1
公开(公告)日：2024-08-01
申请号：US18524803
申请日：2023-11-30
Applicant: NVIDIA Corporation
Inventor： Christopher B. Choy , Or Litany , Charles Loop , Yuke Zhu , Animashree Anandkumar , Wei Dong
CPC classification number: G06T15/20 , G06T1/20 , G06T5/50 , G06T5/70 , G06T7/579 , G06T7/90 , G06T19/20 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084 , G06T2210/04 , G06T2210/21 , G06T2219/2012
Abstract: A technique for reconstructing a three-dimensional scene from monocular video adaptively allocates an explicit sparse-dense voxel grid with dense voxel blocks around surfaces in the scene and sparse voxel blocks further from the surfaces. In contrast to conventional systems, the two-level voxel grid can be efficiently queried and sampled. In an embodiment, the scene surface geometry is represented as a signed distance field (SDF). Representation of the scene surface geometry can be extended to multi-modal data such as semantic labels and color. Because properties stored in the sparse-dense voxel grid structure are differentiable, the scene surface geometry can be optimized via differentiable volume rendering.
-
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.
-
Patent Agency Ranking
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.
-
公开(公告)号：US11062471B1
公开(公告)日：2021-07-13
申请号：US16868342
申请日：2020-05-06
Applicant: NVIDIA Corporation
Inventor： Yiran Zhong , Wonmin Byeon , Charles Loop , Stanley Thomas Birchfield
Abstract: Stereo matching generates a disparity map indicating pixels offsets between matched points in a stereo image pair. A neural network may be used to generate disparity maps in real time by matching image features in stereo images using only 2D convolutions. The proposed method is faster than 3D convolution-based methods, with only a slight accuracy loss and higher generalization capability. A 3D efficient cost aggregation volume is generated by combining cost maps for each disparity level. Different disparity levels correspond to different amounts of shift between pixels in the left and right image pair. In general, each disparity level is inversely proportional to a different distance from the viewpoint.
-
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.
-
公开(公告)号：US11830145B2
公开(公告)日：2023-11-28
申请号：US17479866
申请日：2021-09-20
Applicant: NVIDIA Corporation
Inventor： Kunal Gupta , Shalini De Mello , Charles Loop , Jonathan Tremblay , Stanley Thomas Birchfield
IPC: G06T17/20 , G06N3/08 , G06F18/214
CPC classification number: G06T17/205 , G06F18/214 , G06N3/08
Abstract: A manifold voxel mesh or surface mesh is manufacturable by carving a single block of material and a non-manifold mesh is not manufacturable. Conventional techniques for constructing or extracting a surface mesh from an input point cloud often produce a non-manifold voxel mesh. Similarly, extracting a surface mesh from a voxel mesh that includes non-manifold geometry produces a surface mesh that includes non-manifold geometry. To ensure that the surface mesh includes only manifold geometry, locations of the non-manifold geometry in the voxel mesh are detected and converted into manifold geometry. The result is a manifold voxel mesh from which a manifold surface mesh of the object may be extracted.
-
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
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
10
records
(took 0.038 seconds)
