US Patent Issued to Robert Bosch on May 12 for "Method for omnidirectional dense regression for machine perception tasks via distortion-free CNN and spherical self-attention" (American, Chinese Inventors)

ALEXANDRIA, Va., May 12 -- United States Patent no. 12,626,478, issued on May 12, was assigned to Robert Bosch GmbH (Stuttgart, Germany).

"Method for omnidirectional dense regression for machine perception tasks via distortion-free CNN and spherical self-attention" was invented by Yuliang Guo (Palo Alto, Calif.), Zhixin Yan (Shanghai), Yuyan Li (Columbia, Mo.), Xinyu Huang (San Jose, Calif.) and Liu Ren (Saratoga, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method and device for performing a perception task are disclosed. The method and device incorporate a dense regression model. The dense regression model advantageously incorporates a distortion-free convolution technique that is designed to ac...