公开(公告)号：US20230075664A1

公开(公告)日：2023-03-09

申请号：US17469274

申请日：2021-09-08

Applicant: Peng Cheng Laboratory

Inventor： Tao WEI ,  Yonghong TIAN ,  Yaowei WANG ,  Yun LIANG ,  Chang Wen CHEN ,  Wen GAO

IPC: G06K9/62 ,  G06N3/02

Abstract: Disclosed is a method and system for achieving optimal separable convolutions, the method is applied to image analyzing and processing and comprises steps of: inputting an image to be analyzed and processed; calculating three sets of parameters of a separable convolution: an internal number of groups, a channel size and a kernel size of each separated convolution, and achieving optimal separable convolution process; and performing deep neural network image process. The method and system in the present disclosure adopts implementation of separable convolution which efficiently reduces a computational complexity of deep neural network process. Comparing to the FFT and low rank approximation approaches, the method and system disclosed in the present disclosure is efficient for both small and large kernel sizes and shall not require a pre-trained model to operate on and can be deployed to applications where resources are highly constrained.

公开(公告)号：US20230419554A1

公开(公告)日：2023-12-28

申请号：US18252872

申请日：2020-11-27

Applicant: PENG CHENG LABORATORY

Inventor： Yueru CHEN ,  Jing WANG ,  Wenbo ZHAO ,  Ge LI ,  Wen GAO

IPC: G06T9/00 ,  G06T9/40

CPC classification number: G06T9/001 ,  G06T9/40

Abstract: A point cloud attribute encoding method, a decoding method, an encoding device and a decoding device are disclosed, the point cloud attribute encoding method including: constructing an N-layer binary tree by partitioning a target point cloud according to positions of points within the point cloud, N being an integer greater than 1; for a target node at layer P of the binary tree, obtaining child nodes of the target node, determining a first attribute coefficient and second attribute coefficients of the target node by transforming first attribute coefficients of the child nodes, P being an integer greater than or equal to 1 and less than or equal to N−1; using the first attribute coefficient of a root node and the second attribute coefficients of each target node in the binary tree as output coefficients of the point cloud attribute encoding method.