Data processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a data processing method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring source data corresponding to a three-dimensional object; based on the source data, obtaining first geometric features of nodes of multiple hierarchies with a tree structure corresponding to the source data, wherein the nodes of different hierarchies correspond to different spaces in the three-dimensional space of the three-dimensional object; determining a target node in the plurality of nodes based on the obtained first geometric features of the plurality of nodes, and decoding the feature representation of the target node to obtain second geometric features corresponding to sub-nodes under the target node; and processing the three-dimensional object based on the decoded second geometric feature corresponding to each node to obtain a corresponding processing result. Based on the scheme of the invention, the extraction efficiency and accuracy of the geometric features of the three-dimensional object can be effectively improved, the data processing requirements corresponding to the three-dimensional object are better met, and the processing efficiency and effect are improved.

Description

technical field [0001] The present application relates to the fields of computer, artificial intelligence, and game technologies. Specifically, the present application relates to a data processing method, device, electronic equipment, and storage medium. Background technique [0002] Researching efficient geometric 3D representations (also called 3D representations, geometric features, geometric shape features, geometric representations, geometric shape representations, etc.) is one of the core tasks of computer vision and computer graphics, involving applications from upper layers (e.g., Scene understanding, object recognition, object classification, etc.) to various low-level tasks (including 3D (three-dimensional, three-dimensional) shape reconstruction, interpolation and manipulation, etc.). [0003] In order to adapt to various application scenarios, the research on 3D representation has always been a hot spot for technicians. Although there are many learning methods fo...

AI Technical Summary

Problems solved by technology

[0003] In order to adapt to various application scenarios, the research on 3D representation has always been a hot spot for technicians. Although there are many learning methods for 3D representation, such as point cloud and voxel representation, grid-based learning methods, Recently, learning methods based on neural implicit functions have appeared, but studies have found that the 3D representations learned in various ways are still not ideal in practical applications, and the learning of 3D representations still needs to be improved.

Images