Swreck point cloud completion reconstruction method and system, electronic equipment and storage medium
CN119722927APending Publication Date: 2025-03-28WUHAN UNIV OF TECH
Patent Information
- Application Number
- CN202411692428.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-25
- Publication Date
- 2025-03-28
Smart Images

Figure CN119722927A_ABST
Abstract
The invention discloses a sunken ship point cloud completion reconstruction method and system, an electronic device and a storage medium, and the method comprises the steps: constructing a sunken ship point cloud data set through a preset point cloud database, including an incomplete scanning point cloud data set; preprocessing the incomplete scanning point cloud data set to obtain preset point proxy data; constructing a preset point cloud completion reconstruction network model, and training the preset point cloud completion reconstruction network model through the preset point agent data to obtain a target point cloud completion reconstruction network model; obtaining to-be-complemented ship sinking point cloud data, and inputting the to-be-complemented ship sinking point cloud data into the target point cloud complementation reconstruction network model for point cloud prediction to obtain missing point cloud data; and according to the missing point cloud data and the to-be-complemented shipwreck point cloud data, target shipwreck point cloud data are constructed and obtained. According to the embodiment of the invention, the method can achieve the complementation and reconstruction of the sunken ship point cloud, and effectively improves the accuracy and robustness of the complementation and reconstruction of the sunken ship point cloud. The method can be widely applied to the technical field of computer vision.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Cited By
Point cloud completion method, system and device based on self-supervised learning and medium
CN120182144A