公开(公告)号：US20170263041A1

公开(公告)日：2017-09-14

申请号：US15421364

申请日：2017-01-31

Applicant: NVIDIA Corporation

Inventor： Iuri Frosio ,  Jan Kautz

IPC: G06T15/00 ,  G09G5/36

CPC classification number: G09G5/363 ,  G06T5/002

Abstract: A system, method and computer program product are provided for generating one or more values for a signal patch using neighboring patches collected based on a distance dynamically computed from a noise distribution of the signal patch. In use, a reference patch is identified from a signal, and a reference distance is computed based on a noise distribution in the reference patch. Neighbor patches are then collected from the signal based on the computed reference distance from the reference patch. Further, the collected neighbor patches are processed with the reference patch to generate one or more values for the reference patch.

公开(公告)号：US20160307482A1

公开(公告)日：2016-10-20

申请号：US15130886

申请日：2016-04-15

Applicant: NVIDIA Corporation

Inventor： Fu-Chung Huang ,  David Patrick Luebke ,  Jan Kautz ,  Dawid Stanislaw Pajak

IPC: G09G3/00 ,  G06T15/04 ,  G09G3/36 ,  G06T15/80 ,  G06T15/00 ,  G09G3/34

CPC classification number: G09G3/002 ,  G09G3/001 ,  G09G3/2003 ,  G09G3/2074 ,  G09G3/3406 ,  G09G3/3433 ,  G09G3/36 ,  G09G5/363 ,  G09G5/397 ,  G09G2300/023 ,  G09G2300/0426 ,  G09G2340/0407 ,  G09G2360/08

Abstract: A method, computer readable medium, and system are disclosed for generating mixed-primary data for display. The method includes the steps of receiving a source image that includes a plurality of pixels, dividing the source image into a plurality of blocks, analyzing the source image based on an image decomposition algorithm, encoding chroma information and modulation information to generate a video signal, and transmitting the video signal to a mixed-primary display. The chroma information and modulation information correspond with two or more mixed-primary color components and are generated by the image decomposition algorithm to minimize error between a reproduced image and the source image. The two or more mixed-primary colors selected for each block of the source image are not limited to any particular set of colors and each mixed-primary color component may be selected from any color capable of being reproduced by the mixed-primary display.

Abstract translation: 公开了一种用于生成用于显示的混合主数据的方法，计算机可读介质和系统。 该方法包括以下步骤：接收包括多个像素的源图像，将源图像划分为多个块，基于图像分解算法分析源图像，对色度信息和调制信息进行编码以产生视频信号， 并将视频信号发送到混合主显示器。 色度信息和调制信息与两个或更多个混合原色分量相对应，并且由图像分解算法产生，以最小化再现图像与源图像之间的误差。 为源图像的每个块选择的两个或多个混合原色不限于任何特定的颜色集合，并且可以从能够由混合主显示器再现的任何颜色中选择每个混合原色分量。

公开(公告)号：US20150206504A1

公开(公告)日：2015-07-23

申请号：US14600507

申请日：2015-01-20

Applicant: NVIDIA Corporation

Inventor： Dawid Stanislaw Pajak ,  Felix Heide ,  Nagilla Dikpal Reddy ,  Mushfiqur Rouf ,  Jan Kautz ,  Kari Pulli ,  Orazio Gallo

IPC: G09G5/02 ,  G06T11/00

CPC classification number: G09G5/02 ,  G06T3/4015 ,  G06T5/001 ,  G06T5/002 ,  G09G5/026 ,  G09G5/363 ,  G09G2320/0238 ,  G09G2320/0242 ,  G09G2320/0247 ,  G09G2320/066 ,  G09G2360/08

Abstract: A computer implemented method of determining a latent image from an observed image is disclosed. The method comprises implementing a plurality of image processing operations within a single optimization framework, wherein the single optimization framework comprises solving a linear minimization expression. The method further comprises mapping the linear minimization expression onto at least one non-linear solver. Further, the method comprises using the non-linear solver, iteratively solving the linear minimization expression in order to extract the latent image from the observed image, wherein the linear minimization expression comprises: a data term, and a regularization term, and wherein the regularization term comprises a plurality of non-linear image priors.

Abstract translation: 公开了一种从观察图像确定潜像的计算机实现方法。 该方法包括在单个优化框架内实现多个图像处理操作，其中单个优化框架包括求解线性最小化表达式。 该方法还包括将线性最小化表达映射到至少一个非线性求解器上。 此外，该方法包括使用非线性求解器，迭代地求解线性最小化表达以从观察图像中提取潜像，其中线性最小化表达式包括：数据项和正则化项，其中正则化 术语包括多个非线性图像先验。

公开(公告)号：US12169882B2

公开(公告)日：2024-12-17

申请号：US17929182

申请日：2022-09-01

Applicant: NVIDIA Corporation

Inventor： Sifei Liu ,  Jiteng Mu ,  Shalini De Mello ,  Zhiding Yu ,  Jan Kautz

IPC: G06T11/00 ,  G06T3/18

Abstract: Embodiments of the present disclosure relate to learning dense correspondences for images. Systems and methods are disclosed that disentangle structure and texture (or style) representations of GAN synthesized images by learning a dense pixel-level correspondence map for each image during image synthesis. A canonical coordinate frame is defined and a structure latent code for each generated image is warped to align with the canonical coordinate frame. In sum, the structure associated with the latent code is mapped into a shared coordinate space (canonical coordinate space), thereby establishing correspondences in the shared coordinate space. A correspondence generation system receives the warped coordinate correspondences as an encoded image structure. The encoded image structure and a texture latent code are used to synthesize an image. The shared coordinate space enables propagation of semantic labels from reference images to synthesized images.

公开(公告)号：US20240185034A1

公开(公告)日：2024-06-06

申请号：US18130648

申请日：2023-04-04

Applicant: NVIDIA Corporation

Inventor： Ali Hatamizadeh ,  Gregory Heinrich ,  Hongxu Yin ,  Jose Manuel Alvarez Lopez ,  Jan Kautz ,  Pavlo Molchanov

IPC: G06N3/0455 ,  G06N3/0464 ,  G06N3/08

CPC classification number: G06N3/0455 ,  G06N3/0464 ,  G06N3/08

Abstract: Apparatuses, systems, and techniques of using one or more machine learning processes (e.g., neural network(s)) to process data (e.g., using hierarchical self-attention). In at least one embodiment, image data is classified using hierarchical self-attention generated using carrier tokens that are associated with windowed subregions of the image data, and local attention generated using local tokens within the windowed subregions and the carrier tokens.

公开(公告)号：US11960570B2

公开(公告)日：2024-04-16

申请号：US17412091

申请日：2021-08-25

Applicant: NVIDIA Corporation

Inventor： Taihong Xiao ,  Sifei Liu ,  Shalini De Mello ,  Zhiding Yu ,  Jan Kautz

IPC: G06F18/00 ,  G06F18/213 ,  G06F18/214 ,  G06N3/08 ,  G06V10/22 ,  G06V30/14

CPC classification number: G06F18/2155 ,  G06F18/213 ,  G06N3/08 ,  G06V10/22 ,  G06V30/1444

Abstract: A multi-level contrastive training strategy for training a neural network relies on image pairs (no other labels) to learn semantic correspondences at the image level and region or pixel level. The neural network is trained using contrasting image pairs including different objects and corresponding image pairs including different views of the same object. Conceptually, contrastive training pulls corresponding image pairs closer and pushes contrasting image pairs apart. An image-level contrastive loss is computed from the outputs (predictions) of the neural network and used to update parameters (weights) of the neural network via backpropagation. The neural network is also trained via pixel-level contrastive learning using only image pairs. Pixel-level contrastive learning receives an image pair, where each image includes an object in a particular category.

公开(公告)号：US20240096115A1

公开(公告)日：2024-03-21

申请号：US18243555

申请日：2023-09-07

Applicant: NVIDIA Corporation

Inventor： Pavlo Molchanov ,  Jan Kautz ,  Arash Vahdat ,  Hongxu Yin ,  Paul Micaelli

IPC: G06V20/59 ,  G06T7/70 ,  G06V10/82 ,  G06V20/70 ,  G06V40/16

CPC classification number: G06V20/597 ,  G06T7/70 ,  G06V10/82 ,  G06V20/70 ,  G06V40/171 ,  G06T2207/30201 ,  G06V2201/07

Abstract: Landmark detection refers to the detection of landmarks within an image or a video, and is used in many computer vision tasks such emotion recognition, face identity verification, hand tracking, gesture recognition, and eye gaze tracking. Current landmark detection methods rely on a cascaded computation through cascaded networks or an ensemble of multiple models, which starts with an initial guess of the landmarks and iteratively produces corrected landmarks which match the input more finely. However, the iterations required by current methods typically increase the training memory cost linearly, and do not have an obvious stopping criteria. Moreover, these methods tend to exhibit jitter in landmark detection results for video. The present disclosure improves current landmark detection methods by providing landmark detection using an iterative neural network. Furthermore, when detecting landmarks in video, the present disclosure provides for a reduction in jitter due to reuse of previous hidden states from previous frames.

公开(公告)号：US11907846B2

公开(公告)日：2024-02-20

申请号：US17017597

申请日：2020-09-10

Applicant: NVIDIA CORPORATION

Inventor： Sifei Liu ,  Shalini De Mello ,  Varun Jampani ,  Jan Kautz ,  Xueting Li

IPC: G06K9/36 ,  G06N3/084 ,  G06F18/22 ,  G06F18/20 ,  G06F18/214 ,  G06F18/21 ,  G06N3/045 ,  G06T17/00 ,  G06V10/82

CPC classification number: G06N3/084 ,  G06F18/214 ,  G06F18/2163 ,  G06F18/22 ,  G06F18/29 ,  G06N3/045 ,  G06T17/00 ,  G06V10/82

Abstract: One embodiment of the present invention sets forth a technique for performing spatial propagation. The technique includes generating a first directed acyclic graph (DAG) by connecting spatially adjacent points included in a set of unstructured points via directed edges along a first direction. The technique also includes applying a first set of neural network layers to one or more images associated with the set of unstructured points to generate (i) a set of features for the set of unstructured points and (ii) a set of pairwise affinities between the spatially adjacent points connected by the directed edges. The technique further includes generating a set of labels for the set of unstructured points by propagating the set of features across the first DAG based on the set of pairwise affinities.

公开(公告)号：US20220284232A1

公开(公告)日：2022-09-08

申请号：US17188397

申请日：2021-03-01

Applicant: NVIDIA Corporation

Inventor： Hongxu Yin ,  Arun Mallya ,  Arash Vahdat ,  Jose Manuel Alvarez Lopez ,  Jan Kautz ,  Pavlo Molchanov

IPC: G06K9/62 ,  G06K9/66

Abstract: Apparatuses, systems, and techniques to identify one or more images used to train one or more neural networks. In at least one embodiment, one or more images used to train one or more neural networks are identified, based on, for example, one or more labels of one or more objects within the one or more images.

公开(公告)号：US11375176B2

公开(公告)日：2022-06-28

申请号：US16780738

申请日：2020-02-03

Applicant: NVIDIA Corporation

Inventor： Hung-Yu Tseng ,  Shalini De Mello ,  Jonathan Tremblay ,  Sifei Liu ,  Jan Kautz ,  Stanley Thomas Birchfield

IPC: H04N13/282 ,  H04N13/268 ,  G06K9/62 ,  G06N3/08

Abstract: When an image is projected from 3D, the viewpoint of objects in the image, relative to the camera, must be determined. Since the image itself will not have sufficient information to determine the viewpoint of the various objects in the image, techniques to estimate the viewpoint must be employed. To date, neural networks have been used to infer such viewpoint estimates on an object category basis, but must first be trained with numerous examples that have been manually created. The present disclosure provides a neural network that is trained to learn, from just a few example images, a unique viewpoint estimation network capable of inferring viewpoint estimations for a new object category.