Nvidia Corporation

Brigham Young University

Joshua Abbott

Jonathan B White

James Lewis Van Welzen

Ke Chen

Joachim Pehserl

Amir Akbarzadeh

David Paul Clark

David Wehr

Bryan Stuart Morse

Samuel Rupp Ogden

Cristobal Alvarez-Russell

Nidhi Singh

In various examples, perception of landmark shapes may be used for localization in autonomous systems and applications. In some embodiments, a deep neural network (DNN) is used to generate (e.g., per-point) classifications of measured 3D points (e.g., classified LiDAR points), and a representation of the shape of one or more detected landmarks is regressed from the classifications. For each of one or more classes, the classification data may be thresholded to generate a binary mask and/or dilated to generate a densified representation, and the resulting (e.g., dilated, binary) mask may be clustered into connected components that are iteratively: fitted a shape (e.g., a polynomial or Bezier spline for lane lines, a circle for top-down representations of poles or traffic lights), weighted, and merged. As such, the resulting connected components and their fitted shapes may be used to represent detected landmarks and used for localization, navigation, and/or other uses.

Landmark perception for localization in autonomous systems and applications

One embodiment of the present invention sets forth a technique for broadcasting composited game content. The technique includes executing an application program to generate a first video frame of game content, and causing the first video frame to be displayed on a primary display device. The technique further includes compositing at least one graphical user interface (GUI) element with the first video frame to generate a composited frame. The technique further includes causing the composited frame to be displayed on an external display device by transmitting the composited frame to the external display device via a local display interface.

Gamecasting techniques

A method for applying depth-dependent effects to images includes receiving a stereo image and depth related information extracted from the stereo image, and applying an effect to the stereo image according to the depth related information. The method may also include calculating surface orientation information for the stereo image to improve the depth related information extracted from the stereo image and/or facilitate the application of effects, such as scene relighting, which leverage surface orientation information. In some embodiments, the method includes fitting a curved surface to the depth related information and adjusting the depth related information and/or surface orientation information according to the curved surface. The method may also include processing the depth related information with a bilateral smoothing filter wherein coefficients for neighboring pixels are weighted according to similarity in color and similarity in depth. An apparatus and computer-readable medium corresponding to the above method are also disclosed.

Depth-aware stereo image editing method apparatus and computer-readable medium

Growing community of inventors

Raleigh, NC, United States of America

Joshua Abbott