Hand grasping posture data enhancement method and system based on contact graph

By generating a data-enhanced hand grasping posture model using contact graph technology, the problem of error distribution between hand posture and model posture was solved. This achieved increased data volume and improved generalization ability, ensuring the matching of hand posture and the generation effect.

CN121725152APending Publication Date: 2026-03-24HANGZHOU LINGBO VIRTUAL REALITY TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-24
Publication Date
2026-03-24

AI Technical Summary

Technical Problem

Existing hand grasping posture generation models suffer from errors in hand posture distribution compared to the model's posture distribution during data augmentation due to traditional methods. This results in poor model generalization ability and generation performance, especially when dealing with out-of-dataset models that generate unreasonable postures.

Method used

By using a contact map-based hand grasping posture data augmentation method, a sampled dataset of the target model is obtained, a contact map is generated, and a data-augmented contact model is designed using contact map technology. This includes data processing of point cloud or mesh types, performing expansion operations and geometry generation in the non-contact domain to ensure hand posture matching.

Benefits of technology

It effectively enhances hand pose data, increases the amount of data, improves the generalization and inference capabilities of neural networks, avoids the pose mismatch problem in traditional methods, and improves the generalization ability and generation effect of the model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121725152A_ABST
    Figure CN121725152A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of three-dimensional data processing, particularly provides a hand grasping posture data enhancement method and system based on a contact graph, and aims to solve the problems that errors generally exist between hand postures and posture distribution of a model in an existing data enhancement method; and the generalization ability of the model and the generation effect of the hand grasping posture are poor. In order to achieve the purpose, the method comprises the steps that a sampling data set on a target model is obtained on the basis of the data type of the target model, and the sampling data set at least comprises a plurality of sampling face data sets or a plurality of sampling point data; generating a contact graph based on the sampling data set; and generating a data enhanced contact model based on the data type of the target model and the contact graph. According to the method, the data enhancement of the sampled data is realized, the hand posture corresponding to the original data of the target model is ensured not to have any mismatch, and the data enhancement of the model in the grasping posture data is realized by utilizing the contact graph technology design.
Need to check novelty before this filing date? Find Prior Art