Method, system and device for generating three-dimensional reconstruction model and readable storage medium

Abstract

The invention discloses a three-dimensional reconstruction model generation method, system and device and a readable storage medium. The method comprises the steps that a current symbol distance function value from each space unit to the surface of a first three-dimensional reconstruction model is calculated; performing directional decomposition and directional weighted fusion on each current symbol distance function value and an initial symbol distance function value of the space unit, and updating the initial symbol distance function value into an obtained fusion result; judging whether the current data frame is the last frame or not; and if yes, establishing a second three-dimensional reconstruction model according to each initial symbol distance function value. According to the method, the current symbol distance function value and the initial symbol distance function value are subjected to decomposition and weighted fusion, so that more accurate recording and expression of data in the reconstruction process are realized, the accuracy problem of data recording in the reconstruction process is solved, the problem that details of a reconstruction result are smoothed in the data fusion process is solved, and the reconstruction efficiency is improved. Reconstruction geometric details are better reserved, and the accuracy of the three-dimensional reconstruction model is improved.

Description

technical field [0001] The present application relates to the field of 3D reconstruction models, in particular to a method, system, device and readable storage medium for generating a 3D reconstruction model. Background technique [0002] 3D reconstruction is a technology that uses data collected by various sensors to establish a digital model of a real scene. It involves the intersection of multiple disciplines such as sensing, computer vision, and computer graphics. It has a wide range of applications in many fields such as robotics, autonomous driving, and VR / AR. Applications. The data formats and corresponding reconstruction methods collected by different sensors are different, and the representation formats and application scenarios of the reconstruction models are also different. Generally speaking, the dense model that can reconstruct the scene stably in real time is the goal that people pursue for 3D reconstruction technology. [0003] The existing 3D reconstructio...

AI Technical Summary

Problems solved by technology

However, this representation method will cause the geometric details of the reconstructed object to be lost, resulting in a relatively low accuracy of the reconstructed model.

Images