公开(公告)号：US20210233273A1

公开(公告)日：2021-07-29

申请号：US16752225

申请日：2020-01-24

Applicant: NVIDIA Corporation

Inventor： Adrian Spurr ,  Pavlo Molchanov ,  Umar Iqbal ,  Jan Kautz

IPC: G06T7/73 ,  G06K9/00 ,  G06K9/62

Abstract: Apparatuses, systems, and techniques that determine the pose of a human hand from a 2-D image are described herein. In at least one embodiment, training of a neural network is augmented using weakly labeled or unlabeled pose data which is augmented with losses based on a human hand model.

公开(公告)号：US10929654B2

公开(公告)日：2021-02-23

申请号：US16290643

申请日：2019-03-01

Applicant: NVIDIA Corporation

Inventor： Umar Iqbal ,  Pavlo Molchanov ,  Thomas Michael Breuel ,  Jan Kautz

IPC: G06K9/00 ,  G06N3/08 ,  G06T7/73 ,  G06N5/04 ,  G06T7/579

Abstract: Estimating a three-dimensional (3D) pose of an object, such as a hand or body (human, animal, robot, etc.), from a 2D image is necessary for human-computer interaction. A hand pose can be represented by a set of points in 3D space, called keypoints. Two coordinates (x,y) represent spatial displacement and a third coordinate represents a depth of every point with respect to the camera. A monocular camera is used to capture an image of the 3D pose, but does not capture depth information. A neural network architecture is configured to generate a depth value for each keypoint in the captured image, even when portions of the pose are occluded, or the orientation of the object is ambiguous. Generation of the depth values enables estimation of the 3D pose of the object.

公开(公告)号：US20200334543A1

公开(公告)日：2020-10-22

申请号：US16389832

申请日：2019-04-19

Applicant: NVIDIA Corporation

Inventor： Seonwook Park ,  Shalini De Mello ,  Pavlo Molchanov ,  Umar Iqbal ,  Jan Kautz

IPC: G06N3/08 ,  G06F17/18 ,  G06N3/04 ,  G06F7/57

Abstract: A neural network is trained to identify one or more features of an image. The neural network is trained using a small number of original images, from which a plurality of additional images are derived. The additional images generated by rotating and decoding embeddings of the image in a latent space generated by an autoencoder. The images generated by the rotation and decoding exhibit changes to a feature that is in proportion to the amount of rotation.