Qualcomm Incorporated

Risheek Garrepalli

Jamie Menjay Lin

Fatih Murat Porikli

Debasmit Das

Shubhankar Mangesh Borse

Hong Cai

Rajeswaran Chockalingapuramravindran

Hyojin Park

Kristopher Urquhart

Aspects of the present disclosure relate to a novel framework for integrating both semantic and instance contexts for panoptic segmentation. In one example aspect, a method for processing image data includes: processing semantic feature data and instance feature data with a panoptic encoding generator to generate a panoptic encoding; processing the panoptic encoding to generate a panoptic segmentation features; and generating the panoptic segmentation mask based on the panoptic segmentation features.

Panoptic segmentation with panoptic, instance, and semantic relations

A computer-implemented method includes receiving a first input. The first input is interpolated based on a first shift along a first dimension and a second shift along a second dimension. A first output is generated based on the interpolated first input. The first output corresponds to a vectorized bilinear shift of the first input for use in place of grid sampling algorithms.

Vectorized bilinear shift for replacing grid sampling in optical flow estimation

Growing community of inventors

San Diego, CA, United States of America

Risheek Garrepalli