Nvidia Corporation

Umar Iqbal

Jan Kautz

Pavlo Molchanov

Shalini De Mello

Sifei Liu

Thomas Michael Breuel

Varun Jampani

Ye Yuan

Yun Rong Guo

Seonwook Park

Yang Fu

Cheng Xie

Siva Karthik Mustikovela

A method and system are provided for tracking instances within a sequence of video frames. The method includes the steps of processing an image frame by a backbone network to generate a set of feature maps, processing the set of feature maps by one or more prediction heads, and analyzing the embedding features corresponding to a set of instances in two or more image frames of the sequence of video frames to establish a one-to-one correlation between instances in different image frames. The one or more prediction heads includes an embedding head configured to generate a set of embedding features corresponding to one or more instances of an object identified in the image frame. The method may also include training the one or more prediction heads using a set of annotated image frames and/or a plurality of sequences of unlabeled video frames.

Machine learning framework applied in a semi-supervised setting to perform instance tracking in a sequence of image frames

Apparatuses, systems, and techniques to identify orientations of objects within images. In at least one embodiment, one or more neural networks are trained to identify an orientations of one or more objects based, at least in part, on one or more characteristics of the object other than the object's orientation.

Training and inferencing using a neural network to predict orientations of objects in images

In order to determine accurate three-dimensional (3D) models for objects within a video, the objects are first identified and tracked within the video, and a pose and shape are estimated for these tracked objects. A translation and global orientation are removed from the tracked objects to determine local motion for the objects, and motion infilling is performed to fill in any missing portions for the object within the video. A global trajectory is then determined for the objects within the video, and the infilled motion and global trajectory are then used to determine infilled global motion for the object within the video. This enables the accurate depiction of each object as a 3D pose sequence for that model that accounts for occlusions and global factors within the video.

Performing occlusion-aware global 3D pose and shape estimation of articulated objects

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.

Few-shot training of a neural network

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.

Three-dimensional (3D) pose estimation from a monocular camera

Learning to estimate a 3D body pose, and likewise the pose of any type of object, from a single 2D image is of great interest for many practical graphics applications and generally relies on neural networks that have been trained with sample data which annotates (labels) each sample 2D image with a known 3D pose. Requiring this labeled training data however has various drawbacks, including for example that traditionally used training data sets lack diversity and therefore limit the extent to which neural networks are able to estimate 3D pose. Expanding these training data sets is also difficult since it requires manually provided annotations for 2D images, which is time consuming and prone to errors. The present disclosure overcomes these and other limitations of existing techniques by providing a model that is trained from unlabeled multi-view data for use in 3D pose estimation.

3D human body pose estimation using a model trained from unlabeled multi-view data

Estimating a three-dimensional (3D) pose and shape of an articulated body mesh is useful for many different applications including health and fitness, entertainment, and computer graphics. A set of estimated 3D keypoint positions for a human body structure are processed to compute parameters defining the pose and shape of a parametric human body mesh using a set of geometric operations. During processing, 3D keypoints are extracted from the parametric human body mesh and a set of rotations are computed to align the extracted 3D keypoints with the estimated 3D keypoints. The set of rotations may correctly position a particular 3D keypoint location at a 'joint', but an arbitrary number of rotations of the 'joint' keypoint may produce a twist in a connection to a child keypoint. Rules are applied to the set of rotations to resolve ambiguous twists and articulate the parametric human body mesh according to the computed parameters.

Growing community of inventors

San Jose, CA, United States of America

Umar Iqbal