公开(公告)号：US20230095092A1

公开(公告)日：2023-03-30

申请号：US17957143

申请日：2022-09-30

Applicant: Nvidia Corporation

Inventor： Zhisheng Xiao ,  Karsten Kreis ,  Arash Vahdat

IPC: G06T5/00

Abstract: Apparatuses, systems, and techniques are presented to train and utilize one or more neural networks. A denoising diffusion generative adversarial network (denoising diffusion GAN) reduces a number of denoising steps during a reverse process. The denoising diffusion GAN does not assume a Gaussian distribution for large steps of the denoising process and applies a multi-model model to permit denoising with fewer steps. Systems and methods further minimize a divergence between a diffused real data distribution and a diffused generator distribution over several timesteps. Accordingly, various embodiments may enable faster sample generation, in which the samples are generated from noise using the denoising diffusion GAN.

公开(公告)号：US12249048B2

公开(公告)日：2025-03-11

申请号：US17681625

申请日：2022-02-25

Applicant: NVIDIA CORPORATION

Inventor： Arash Vahdat ,  Karsten Kreis ,  Jan Kautz

IPC: G06T5/70 ,  G06N3/08 ,  G06V10/82

Abstract: One embodiment of the present invention sets forth a technique for generating data. The technique includes sampling from a first distribution associated with the score-based generative model to generate a first set of values. The technique also includes performing one or more denoising operations via the score-based generative model to convert the first set of values into a first set of latent variable values associated with a latent space. The technique further includes converting the first set of latent variable values into a generative output.

公开(公告)号：US20220383570A1

公开(公告)日：2022-12-01

申请号：US17827394

申请日：2022-05-27

Applicant: NVIDIA Corporation

Inventor： Huan Ling ,  Karsten Kreis ,  Daiqing Li ,  Seung Wook Kim ,  Antonio Torralba Barriuso ,  Sanja Fidler

IPC: G06T11/60 ,  G06T7/10 ,  G06V10/776 ,  G06V10/774

Abstract: In various examples, high-precision semantic image editing for machine learning systems and applications are described. For example, a generative adversarial network (GAN) may be used to jointly model images and their semantic segmentations based on a same underlying latent code. Image editing may be achieved by using segmentation mask modifications (e.g., provided by a user, or otherwise) to optimize the latent code to be consistent with the updated segmentation, thus effectively changing the original, e.g., RGB image. To improve efficiency of the system, and to not require optimizations for each edit on each image, editing vectors may be learned in latent space that realize the edits, and that can be directly applied on other images with or without additional optimizations. As a result, a GAN in combination with the optimization approaches described herein may simultaneously allow for high precision editing in real-time with straightforward compositionality of multiple edits.

公开(公告)号：US20240161403A1

公开(公告)日：2024-05-16

申请号：US18232279

申请日：2023-08-09

Applicant: NVIDIA Corporation

Inventor： Chen-Hsuan Lin ,  Tsung-Yi Lin ,  Ming-Yu Liu ,  Sanja Fidler ,  Karsten Kreis ,  Luming Tang ,  Xiaohui Zeng ,  Jun Gao ,  Xun Huang ,  Towaki Takikawa

IPC: G06T17/20 ,  G06T3/40 ,  G06T15/04 ,  G06T17/00 ,  G06T19/20

CPC classification number: G06T17/20 ,  G06T3/40 ,  G06T15/04 ,  G06T17/005 ,  G06T19/20

Abstract: Text-to-image generation generally refers to the process of generating an image from one or more text prompts input by a user. While artificial intelligence has been a valuable tool for text-to-image generation, current artificial intelligence-based solutions are more limited as it relates to text-to-3D content creation. For example, these solutions are oftentimes category-dependent, or synthesize 3D content at a low resolution. The present disclosure provides a process and architecture for high-resolution text-to-3D content creation.

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：US12288277B2

公开(公告)日：2025-04-29

申请号：US17827394

申请日：2022-05-27

Applicant: NVIDIA Corporation

Inventor： Huan Ling ,  Karsten Kreis ,  Daiqing Li ,  Seung Wook Kim ,  Antonio Torralba Barriuso ,  Sanja Fidler

IPC: G06T7/10 ,  G06T11/60 ,  G06V10/774 ,  G06V10/776

Abstract: In various examples, high-precision semantic image editing for machine learning systems and applications are described. For example, a generative adversarial network (GAN) may be used to jointly model images and their semantic segmentations based on a same underlying latent code. Image editing may be achieved by using segmentation mask modifications (e.g., provided by a user, or otherwise) to optimize the latent code to be consistent with the updated segmentation, thus effectively changing the original, e.g., RGB image. To improve efficiency of the system, and to not require optimizations for each edit on each image, editing vectors may be learned in latent space that realize the edits, and that can be directly applied on other images with or without additional optimizations. As a result, a GAN in combination with the optimization approaches described herein may simultaneously allow for high precision editing in real-time with straightforward compositionality of multiple edits.