Three-dimensional reconstruction method and device, equipment, storage medium and computer program

By excluding pixel points in candidate foreground areas in three-dimensional reconstruction, the problem of poor quality of three-dimensional reconstruction caused by foreground object interference is solved, and a higher quality three-dimensional reconstruction of target objects is achieved.

CN119722914AActive Publication Date: 2025-03-28HUAWEI TECH CO LTD
8 Cites 1 Cited by

Patent Information

Application Number
CN202311289044.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-09-28
Publication Date
2025-03-28
Estimated Expiration
2043-09-28

AI Technical Summary

Technical Problem

In the prior art, the quality of three-dimensional reconstruction is poor, mainly due to interference from foreground objects.

Method used

By determining candidate foreground areas based on multiple captured images, excluding pixel points in these areas, and using a neural radiation field model to perform three-dimensional reconstruction of the target object.

Benefits of technology

It effectively improves the three-dimensional reconstruction quality of the target object, avoids interference from foreground objects, and ensures the integrity of billboards and target objects with reflection capabilities after reconstruction.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a three-dimensional reconstruction method and device, equipment, a storage medium and a computer program, and belongs to the technical field of computer vision. The method comprises the steps of determining a plurality of candidate foreground areas based on a plurality of shot images, determining three-dimensional surface coordinates and / or depths of pixel points in the plurality of candidate foreground areas, determining at least one target foreground area from the plurality of candidate foreground areas based on the three-dimensional surface coordinates and / or depths of the pixel points in the plurality of candidate foreground areas, and performing three-dimensional reconstruction on the target object based on pixel points except the at least one target foreground area in the plurality of shot images. According to the method, three-dimensional reconstruction can be performed on the target object based on the pixel points except the at least one target foreground area in the plurality of shot images, so that interference of the foreground object on three-dimensional reconstruction of the target object is avoided, and the three-dimensional reconstruction quality of the target object is effectively improved.
Need to check novelty before this filing date? Find Prior Art