公开(公告)号：US20250142145A1

公开(公告)日：2025-05-01

申请号：US19010882

申请日：2025-01-06

Applicant: NVIDIA Corporation

Inventor： Karsten Julian Kreis ,  Robin Rombach ,  Andreas Blattmann ,  Seung Wook Kim ,  Huan Ling ,  Sanja Fidler ,  Tim Dockhorn

IPC: H04N21/2343 ,  G06T9/00 ,  G06V10/24 ,  G06V10/25 ,  G06V10/82 ,  H04N7/01

Abstract: In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.

公开(公告)号：US12192547B2

公开(公告)日：2025-01-07

申请号：US18181729

申请日：2023-03-10

Applicant: NVIDIA Corporation

Inventor： Karsten Julian Kreis ,  Robin Rombach ,  Andreas Blattmann ,  Seung Wook Kim ,  Huan Ling ,  Sanja Fidler ,  Tim Dockhorn

IPC: H04N21/2343 ,  G06T9/00 ,  G06V10/24 ,  G06V10/25 ,  G06V10/82 ,  H04N7/01

Abstract: In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.

公开(公告)号：US20230377099A1

公开(公告)日：2023-11-23

申请号：US18319986

申请日：2023-05-18

Applicant: Nvidia Corporation

Inventor： Karsten Julian Kreis ,  Tim Dockhorn ,  Arash Vahdat

IPC: G06T5/00 ,  G06T7/64 ,  G06T11/00 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06T5/002 ,  G06T7/64 ,  G06T11/00 ,  G06N3/045 ,  G06N3/08 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06T2207/30241 ,  G06T2200/28

Abstract: Approaches presented herein provide for the generation of synthesized data from input noise using a denoising diffusion network. A higher order differential equation solver can be used for the denoising process, with one or more higher-order terms being distilled into one or more separate efficient neural networks. A separate, efficient neural network can be called together with a primary denoising model at inference time without significant loss in sampling efficiency. The separate neural network can provide information about the curvature (or other higher-order term) of the differential equation, representing a denoising trajectory, that can be used by the primary diffusion network to denoise the image using fewer denoising iterations.

公开(公告)号：US12299962B2

公开(公告)日：2025-05-13

申请号：US17959915

申请日：2022-10-04

Applicant: Nvidia Corporation

Inventor： Karsten Kreis ,  Tim Dockhorn ,  Arash Vahdat

IPC: G06V10/774 ,  G06N3/045 ,  G06N3/047 ,  G06T7/277

Abstract: Systems and methods described relate to the synthesis of content using generative models. In at least one embodiment, a score-based generative model can use a stochastic differential equation with critically-damped Langevin diffusion to learn to synthesize content. During a forward diffusion process, noise can be introduced into a set of auxiliary (e.g., “velocity”) values for an input image to learn a score function. This score function can be used with the stochastic differential equation during a reverse diffusion denoising process to remove noise from the image to generate a reconstructed version of the input image. A score matching objective for the critically-damped Langevin diffusion process can require only the conditional distribution learned from the velocity data. A stochastic differential equation based integrator can then allow for efficient sampling from these critically-damped Langevin diffusion models.

公开(公告)号：US20240171788A1

公开(公告)日：2024-05-23

申请号：US18181729

申请日：2023-03-10

Applicant: NVIDIA Corporation

Inventor： Karsten Julian Kreis ,  Robin Rombach ,  Andreas Blattmann ,  Seung Wook Kim ,  Huan Ling ,  Sanja Fidler ,  Tim Dockhorn

IPC: H04N21/2343 ,  G06T9/00 ,  G06V10/24 ,  G06V10/25 ,  G06V10/82 ,  H04N7/01

CPC classification number: H04N21/234363 ,  G06T9/00 ,  G06V10/24 ,  G06V10/25 ,  G06V10/82 ,  H04N7/0117

Abstract: In various examples, systems and methods are disclosed relating to aligning images into frames of a first video using at least one first temporal attention layer of a neural network model. The first video has a first spatial resolution. A second video having a second spatial resolution is generated by up-sampling the first video using at least one second temporal attention layer of an up-sampler neural network model, wherein the second spatial resolution is higher than the first spatial resolution.