-
公开(公告)号：US20220068013A1
公开(公告)日：2022-03-03
申请号：US17006548
申请日：2020-08-28
Applicant: NVIDIA Corporation
Inventor： Pawel Kozlowski , Maksim Aizenshtein
Abstract: Systems and methods for improving quality of rendered images. Temporal accumulation using jittered motion vectors may be performed in intermediate passes.
-
公开(公告)号：US20220189114A1
公开(公告)日：2022-06-16
申请号：US17548038
申请日：2021-12-10
Applicant: NVIDIA Corporation
Inventor： Maksim Aizenshtein
Abstract: Systems and methods are provided to perform constrained BSDF sampling in relation to various algorithms, and specifically in relation to ray tracing algorithms. In some embodiments, a method is provided to generate samples by: determining a spherical polygon on a unit hemisphere; determining, on a unit circle, a projected area corresponding to the spherical polygon on the unit hemisphere; determining a parameterization of the projected area of the spherical polygon on the unit circle; generating samples in the projected area based on the parameterization; and generating samples in the spherical polygon. The unit circle is abase of the unit hemisphere, and the projection of the projected area is along a vector perpendicular to the unit circle. The generated samples in the spherical polygon correspond to the samples in the projected area. The method may further include evaluating a rendering equation based on the generated samples in the spherical polygon.
-
Patent Agency Ranking
公开(公告)号：US20250148691A1
公开(公告)日：2025-05-08
申请号：US18500852
申请日：2023-11-02
Applicant: Nvidia Corporation
Inventor： Maksim Aizenshtein
Abstract: Approaches presented herein provide for removal or reduction of anti-aliasing artifacts, such as Moiré patterns or staircasing, in an image to be rendered. In many instances, these artifacts correspond to regular texture patterns with fine detail, and the addition of randomization in sampling position can help to remove the impact of the regularity of the pattern. In at least one embodiment, a first order approximation can be used that introduces a random amount of shifting determined using texture coordinate derivatives. The random amount can account for any jitter offset, and shift the texture coordinates by the determined random amount, such that sample selected for that pixel will select from a sample location that corresponds to the random shift but is constrained to be within the bounds of the pixel.
-
公开(公告)号：US20230281906A1
公开(公告)日：2023-09-07
申请号：US17686081
申请日：2022-03-03
Applicant: Nvidia Corporation
Inventor： Pawel Kozlowski , Maksim Aizenshtein
Abstract: Systems and methods relate to the determination of accurate motion vectors, for rendering situations such as a noisy Monte Carlo integration where image object surfaces are at least partially translucent. To optimize the search for “real world” positions, this invention defines the background as first path vertices visible through multiple layers of refractive interfaces. To find matching world positions, the background is treated as a single layer morphing in a chaotic way, permitting the optimized algorithm to be executed only once. Further improving performance over the prior linear gradient descent, the present techniques can apply a cross function and numerical optimization, such as Newton's quadratic target or other convergence function, to locate pixels via a vector angle minimization. Determined motion vectors can then serve as input for services including image denoising.
-
公开(公告)号：US20240177394A1
公开(公告)日：2024-05-30
申请号：US18527770
申请日：2023-12-04
Applicant: Nvidia Corporation
Inventor： Pawel Kozlowski , Maksim Aizenshtein
Abstract: Systems and methods relate to the determination of accurate motion vectors, for rendering situations such as a noisy Monte Carlo integration where image object surfaces are at least partially translucent. To optimize the search for “real world” positions, this invention defines the background as first path vertices visible through multiple layers of refractive interfaces. To find matching world positions, the background is treated as a single layer morphing in a chaotic way, permitting the optimized algorithm to be executed only once. Further improving performance over the prior linear gradient descent, the present techniques can apply a cross function and numerical optimization, such as Newton's quadratic target or other convergence function, to locate pixels via a vector angle minimization. Determined motion vectors can then serve as input for services including image denoising.
-
公开(公告)号：US11935194B2
公开(公告)日：2024-03-19
申请号：US17548038
申请日：2021-12-10
Applicant: NVIDIA Corporation
Inventor： Maksim Aizenshtein
CPC classification number: G06T17/20 , G06T15/005 , G06T15/06 , G06T15/30 , G06T15/50
Abstract: Systems and methods are provided to perform constrained BSDF sampling in relation to various algorithms, and specifically in relation to ray tracing algorithms. In some embodiments, a method is provided to generate samples by: determining a spherical polygon on a unit hemisphere; determining, on a unit circle, a projected area corresponding to the spherical polygon on the unit hemisphere; determining a parameterization of the projected area of the spherical polygon on the unit circle; generating samples in the projected area based on the parameterization; and generating samples in the spherical polygon. The unit circle is abase of the unit hemisphere, and the projection of the projected area is along a vector perpendicular to the unit circle. The generated samples in the spherical polygon correspond to the samples in the projected area. The method may further include evaluating a rendering equation based on the generated samples in the spherical polygon.
-
公开(公告)号：US11836844B2
公开(公告)日：2023-12-05
申请号：US17686081
申请日：2022-03-03
Applicant: Nvidia Corporation
Inventor： Pawel Kozlowski , Maksim Aizenshtein
Abstract: Systems and methods relate to the determination of accurate motion vectors, for rendering situations such as a noisy Monte Carlo integration where image object surfaces are at least partially translucent. To optimize the search for “real world” positions, this invention defines the background as first path vertices visible through multiple layers of refractive interfaces. To find matching world positions, the background is treated as a single layer morphing in a chaotic way, permitting the optimized algorithm to be executed only once. Further improving performance over the prior linear gradient descent, the present techniques can apply a cross function and numerical optimization, such as Newton's quadratic target or other convergence function, to locate pixels via a vector angle minimization. Determined motion vectors can then serve as input for services including image denoising.
-
-
-
-
-
-
Search Results
7
records
(took 0.015 seconds)
