-
公开(公告)号：US20230082536A1
公开(公告)日：2023-03-16
申请号：US17821956
申请日：2022-08-24
申请人： NVIDIA Corporation
摘要： A system, apparatus, and method are provided for performing fast re-training of fully fused neural networks configured to implement at least a portion of a transceiver. At least one of a demapping module, an equalization module, or a channel estimation module can be implemented, at least in part, using a fully fused neural network. The neural network can be trained online during operation by acquiring training data sets using a number of received frames of data. Re-training of the neural network is performed periodically to adapt the neural network to changing channel characteristics. In various embodiments, a neural demapper, a neural channel estimator, and a neural receiver are disclosed to replace or augment one or more components of the transceiver. In another embodiment, an auto-encoder can be implemented across a transmitter and receiver to replace most of the components of the transceiver, the auto-encoder being trained via an end-to-end learning algorithm.
-
公开(公告)号：US20240354912A1
公开(公告)日：2024-10-24
申请号：US18760184
申请日：2024-07-01
申请人： NVIDIA Corporation
CPC分类号： G06T5/77 , G06T11/001 , G06T2207/10024 , G06T2207/20084
摘要： In photorealistic image synthesis by light transport simulation, the colors of each pixel are an integral of a high-dimensional function. However, the functions to integrate contain discontinuities that cannot be predicted efficiently. In practice, the pixel colors are estimated by using Monte Carlo and quasi-Monte Carlo methods to sample light transport paths that connect light sources and cameras and summing up the contributions to evaluate an integral. Because of the sampling, images appear noisy when the number of samples is insufficient. A rank-1 lattice sequence provides sample locations and these sample locations can be enumerated (assigned or distributed to pixels) according to a space-filling curve superimposed on a pixel grid. Combinations of space-filling curves and rank-1 lattice sequences reduce correlations, are deterministic, and may be executed for each pixel in parallel. The rank-1 lattice sequence enables real-time light transport simulation, producing high visual quality even for low sampling rates.
-
公开(公告)号：US20240265619A1
公开(公告)日：2024-08-08
申请号：US18509428
申请日：2023-11-15
申请人： NVIDIA Corporation
发明人： Faycal Ait Aoudia , Jakob Richard Hoydis , Nikolaus Binder , Merlin Nimier-David , Sebastian Cammerer , Alexander Georg Keller , Guillermo Anibal Marcus Martinez
摘要： Embodiments of the present disclosure relate to learning digital twins of radio environments. Differentiable ray tracing may be used to refine the scene geometry of the physical environment, to learn or optimize the scene properties of objects in the scene, to learn or optimize the scene properties of antennas, and to learn or optimize antenna patterns, array geometries, and orientations and positions of transmitters and receivers. Once scene properties have been learned or optimized, the differentiable ray tracer may further be used to simulate radio wave propagation to simulate the performance of different configurations of the scene geometry and radio devices, such as antennas. In an embodiment, one or more of the scene geometry, scene properties, and antenna characteristics are computed by a differentiable parametric function, such as a neural network, etc. and parameters of the differentiable parametric function are learned using the differentiable ray tracing.
-
公开(公告)号：US20230230310A1
公开(公告)日：2023-07-20
申请号：US18184519
申请日：2023-03-15
申请人： NVIDIA Corporation
发明人： Thomas Müller , Nikolaus Binder , Fabrice Pierre Armand Rousselle , Jan Novák , Alexander Georg Keller
CPC分类号： G06T15/005 , G06T15/06 , G06T15/506 , G06N3/10 , G06T2210/52
摘要： 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：US20230052645A1
公开(公告)日：2023-02-16
申请号：US17672566
申请日：2022-02-15
申请人： NVIDIA Corporation
发明人： Alexander Georg Keller , Alex John Bauld Evans , Thomas Müller-Höhne , Faycal Ait Aoudia , Nikolaus Binder , Jakob Hoydis , Christoph Hermann Schied , Sebastian Cammerer , Matthijs van Keirsbilck , Guillermo Anibal Marcus Martinez
摘要： Neural network performance is improved in terms of training speed and/or accuracy by encoding (mapping) inputs to the neural network into a higher dimensional space via a hash function. The input comprises coordinates used to identify a point within a d-dimensional space (e.g., 3D space). The point is quantized and a set of vertex coordinates corresponding to the point are input to a hash function. For example, for d=3, space may be partitioned into axis-aligned voxels of identical size and vertex coordinates of a voxel containing the point are input to the hash function to produce a set of encoded coordinates. The set of encoded coordinates is used to lookup D-dimensional feature vectors in a table of size T that have been learned. The learned feature vectors are filtered (e.g., linearly interpolated, etc.) based on the coordinates of the point to compute a feature vector corresponding to the point.
-
公开(公告)号：US20210294945A1
公开(公告)日：2021-09-23
申请号：US17083787
申请日：2020-10-29
申请人： NVIDIA Corporation
摘要： 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.
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.024 秒)
