ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,900, issued on Sept. 15, was assigned to QUALCOMM Inc. (San Diego).

"Attention-based refinement for depth completion" was invented by Yunxiao Shi (San Diego), Hong Cai (San Diego) and Fatih Murat Porikli (San Diego).

According to the abstract* released by the U.S. Patent & Trademark Office: "A processor-implemented method for attention-based depth completion includes receiving, by an artificial neural network (ANN), an input. The input includes an image and a sparse depth measurement. The ANN extracts multi-scale visual features of the input. The ANN applies a self-attention mechanism to the multi-scale visual features to generate a set of attended multi-scale visual features. T...