-
公开(公告)号：US20220284657A1
公开(公告)日：2022-09-08
申请号：US17340222
申请日：2021-06-07
Applicant: NVIDIA Corporation
Inventor： Thomas Müller , Fabrice Pierre Armand Rousselle , Jan Novák , Alexander Georg Keller
Abstract: A real-time neural radiance caching technique for path-traced global illumination is implemented using a neural network for caching scattered radiance components of global illumination. The neural (network) radiance cache handles fully dynamic scenes, and makes no assumptions about the camera, lighting, geometry, and materials. In contrast with conventional caching, the data-driven approach sidesteps many difficulties of caching algorithms, such as locating, interpolating, and updating cache points. The neural radiance cache is trained via online learning during rendering. Advantages of the neural radiance cache are noise reduction and real-time performance. Importantly, the runtime overhead and memory footprint of the neural radiance cache are stable and independent of scene complexity.
-
公开(公告)号：US20230230310A1
公开(公告)日：2023-07-20
申请号：US18184519
申请日：2023-03-15
Applicant: NVIDIA Corporation
Inventor： Thomas Müller , Nikolaus Binder , Fabrice Pierre Armand Rousselle , Jan Novák , Alexander Georg Keller
CPC classification number: G06T15/005 , G06T15/06 , G06T15/506 , G06N3/10 , G06T2210/52
Abstract: A fully-connected neural network may be configured for execution by a processor as a fully-fused neural network by limiting slow global memory accesses to reading and writing inputs to and outputs from the fully-connected neural network. The computational cost of fully-connected neural networks scale quadratically with its width, whereas its memory traffic scales linearly. Modern graphics processing units typically have much greater computational throughput compared with memory bandwidth, so that for narrow, fully-connected neural networks, the linear memory traffic is the bottleneck. The key to improving performance of the fully-connected neural network is to minimize traffic to slow “global” memory (off-chip memory and high-level caches) and to fully utilize fast on-chip memory (low-level caches, “shared” memory, and registers), which is achieved by the fully-fused approach. A real-time neural radiance caching technique for path-traced global illumination is implemented using the fully-fused neural network for caching scattered radiance components of global illumination.
-
公开(公告)号：US20210294945A1
公开(公告)日：2021-09-23
申请号：US17083787
申请日：2020-10-29
Applicant: NVIDIA Corporation
Inventor： Thomas Müller , Fabrice Pierre Armand Rousselle , Alexander Georg Keller , Jan Novák
Abstract: Monte Carlo and quasi-Monte Carlo integration are simple numerical recipes for solving complicated integration problems, such as valuating financial derivatives or synthesizing photorealistic images by light transport simulation. A drawback of a straightforward application of (quasi-)Monte Carlo integration is the relatively slow convergence rate that manifests as high error of Monte Carlo estimators. Neural control variates may be used to reduce error in parametric (quasi-)Monte Carlo integration—providing more accurate solutions in less time. A neural network system has sufficient approximation power for estimating integrals and is efficient to evaluate. The efficiency results from the use of a first neural network that infers the integral of the control variate and using normalizing flows to model a shape of the control variate.
-
公开(公告)号：US11935179B2
公开(公告)日：2024-03-19
申请号：US18184519
申请日：2023-03-15
Applicant: NVIDIA Corporation
Inventor： Thomas Müller , Nikolaus Binder , Fabrice Pierre Armand Rousselle , Jan Novák , Alexander Georg Keller
CPC classification number: G06T15/06 , G06N3/10 , G06T15/005 , G06T15/506 , G06T2210/52
Abstract: A fully-connected neural network may be configured for execution by a processor as a fully-fused neural network by limiting slow global memory accesses to reading and writing inputs to and outputs from the fully-connected neural network. The computational cost of fully-connected neural networks scale quadratically with its width, whereas its memory traffic scales linearly. Modern graphics processing units typically have much greater computational throughput compared with memory bandwidth, so that for narrow, fully-connected neural networks, the linear memory traffic is the bottleneck. The key to improving performance of the fully-connected neural network is to minimize traffic to slow “global” memory (off-chip memory and high-level caches) and to fully utilize fast on-chip memory (low-level caches, “shared” memory, and registers), which is achieved by the fully-fused approach. A real-time neural radiance caching technique for path-traced global illumination is implemented using the fully-fused neural network for caching scattered radiance components of global illumination.
-
公开(公告)号：US20240020443A1
公开(公告)日：2024-01-18
申请号：US18478025
申请日：2023-09-29
Applicant: NVIDIA Corporation
Inventor： Thomas Müller , Fabrice Pierre Armand Rousselle , Alexander Georg Keller , Jan Novák
CPC classification number: G06F30/27 , G06T15/06 , G06F17/11 , G06T15/506 , G06N3/045 , G06F2111/10
Abstract: Monte Carlo and quasi-Monte Carlo integration are simple numerical recipes for solving complicated integration problems, such as valuating financial derivatives or synthesizing photorealistic images by light transport simulation. A drawback of a straightforward application of (quasi-)Monte Carlo integration is the relatively slow convergence rate that manifests as high error of Monte Carlo estimators. Neural control variates may be used to reduce error in parametric (quasi-)Monte Carlo integration—providing more accurate solutions in less time. A neural network system has sufficient approximation power for estimating integrals and is efficient to evaluate. The efficiency results from the use of a first neural network that infers the integral of the control variate and using normalizing flows to model a shape of the control variate.
-
Patent Agency Ranking
公开(公告)号：US20240257437A1
公开(公告)日：2024-08-01
申请号：US18418680
申请日：2024-01-22
Applicant: NVIDIA Corporation
Inventor： Karthik Vaidyanathan , Alex John Bauld Evans , Jan Novák , Andrea Weidlich , Fabrice Pierre Armand Rousselle , Aaron Eliot Lefohn , Franz Petrik Clarberg , Benedikt Bitterli , Tizian Lucien Zeltner
CPC classification number: G06T15/06 , G06T7/33 , G06T7/40 , G06T15/506 , G06T2207/20081 , G06T2207/20084
Abstract: Embodiments of the present disclosure relate to real-time neural appearance models. Using a neural decoder, scenes are rendered in real-time with complex material appearance previously reserved for offline use. Learned hierarchical textures representing the material properties are encoded as latent codes. When a ray is cast and intersects with geometry in the scene, the intersection point is mapped to one of the latent codes. The latent code is interpreted using neural decoders, which produce reflectance values and importance-sampled directions that can be used to determine a pixel color.
-
公开(公告)号：US20220284658A1
公开(公告)日：2022-09-08
申请号：US17340283
申请日：2021-06-07
Applicant: NVIDIA Corporation
Inventor： Thomas Müller , Nikolaus Binder , Fabrice Pierre Armand Rousselle , Jan Novák , Alexander Georg Keller
Abstract: A fully-connected neural network may be configured for execution by a processor as a fully-fused neural network by limiting slow global memory accesses to reading and writing inputs to and outputs from the fully-connected neural network. The computational cost of fully-connected neural networks scale quadratically with its width, whereas its memory traffic scales linearly. Modern graphics processing units typically have much greater computational throughput compared with memory bandwidth, so that for narrow, fully-connected neural networks, the linear memory traffic is the bottleneck. The key to improving performance of the fully-connected neural network is to minimize traffic to slow “global” memory (off-chip memory and high-level caches) and to fully utilize fast on-chip memory (low-level caches, “shared” memory, and registers), which is achieved by the fully-fused approach. A real-time neural radiance caching technique for path-traced global illumination is implemented using the fully-fused neural network for caching scattered radiance components of global illumination.
-
公开(公告)号：US11816404B2
公开(公告)日：2023-11-14
申请号：US17083787
申请日：2020-10-29
Applicant: NVIDIA Corporation
Inventor： Thomas Müller , Fabrice Pierre Armand Rousselle , Alexander Georg Keller , Jan Novák
CPC classification number: G06F30/27 , G06F17/11 , G06N3/045 , G06T15/06 , G06T15/506 , G06F2111/10
Abstract: Monte Carlo and quasi-Monte Carlo integration are simple numerical recipes for solving complicated integration problems, such as valuating financial derivatives or synthesizing photorealistic images by light transport simulation. A drawback of a straightforward application of (quasi-)Monte Carlo integration is the relatively slow convergence rate that manifests as high error of Monte Carlo estimators. Neural control variates may be used to reduce error in parametric (quasi-)Monte Carlo integration—providing more accurate solutions in less time. A neural network system has sufficient approximation power for estimating integrals and is efficient to evaluate. The efficiency results from the use of a first neural network that infers the integral of the control variate and using normalizing flows to model a shape of the control variate.
-
公开(公告)号：US11631210B2
公开(公告)日：2023-04-18
申请号：US17340283
申请日：2021-06-07
Applicant: NVIDIA Corporation
Inventor： Thomas Müller , Nikolaus Binder , Fabrice Pierre Armand Rousselle , Jan Novák , Alexander Georg Keller
Abstract: A fully-connected neural network may be configured for execution by a processor as a fully-fused neural network by limiting slow global memory accesses to reading and writing inputs to and outputs from the fully-connected neural network. The computational cost of fully-connected neural networks scale quadratically with its width, whereas its memory traffic scales linearly. Modern graphics processing units typically have much greater computational throughput compared with memory bandwidth, so that for narrow, fully-connected neural networks, the linear memory traffic is the bottleneck. The key to improving performance of the fully-connected neural network is to minimize traffic to slow “global” memory (off-chip memory and high-level caches) and to fully utilize fast on-chip memory (low-level caches, “shared” memory, and registers), which is achieved by the fully-fused approach. A real-time neural radiance caching technique for path-traced global illumination is implemented using the fully-fused neural network for caching scattered radiance components of global illumination.
-
公开(公告)号：US11610360B2
公开(公告)日：2023-03-21
申请号：US17340222
申请日：2021-06-07
Applicant: NVIDIA Corporation
Inventor： Thomas Müller , Fabrice Pierre Armand Rousselle , Jan Novák , Alexander Georg Keller
Abstract: A real-time neural radiance caching technique for path-traced global illumination is implemented using a neural network for caching scattered radiance components of global illumination. The neural (network) radiance cache handles fully dynamic scenes, and makes no assumptions about the camera, lighting, geometry, and materials. In contrast with conventional caching, the data-driven approach sidesteps many difficulties of caching algorithms, such as locating, interpolating, and updating cache points. The neural radiance cache is trained via online learning during rendering. Advantages of the neural radiance cache are noise reduction and real-time performance. Importantly, the runtime overhead and memory footprint of the neural radiance cache are stable and independent of scene complexity.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.015 seconds)
