High-resolution human body real-time dynamic reconstruction method and device based on hash table

Abstract

The invention discloses a high-resolution human body real-time dynamic reconstruction method and device based on a hash table. The high-resolution human body real-time dynamic reconstruction method comprises the steps: collecting a plurality of depth images of a single human body through a depth camera; projecting each depth image to a three-dimensional space through camera internal parameters toobtain three-dimensional point clouds, and solving corresponding points between the three-dimensional point clouds and the vertexes of the reconstruction model and between the three-dimensional pointclouds and the embedded human body parameterized model; establishing an energy function according to the corresponding points, carrying out optimal solution to obtain the posture of the human body parameterized model, and further obtaining the non-rigid transformation parameters of each vertex of the reconstructed model; and performing non-rigid transformation on the reconstruction model, so thatthe reconstruction model is transformed to a real-time frame, and the reconstruction model allocates a video memory space for newly added voxels in the hash table, and voxel fusion is performed on allvoxels in the hash table according to the non-rigid transformation parameters, and a human body reconstruction model is obtained to dynamically reconstruct a human body. The high-resolution human body real-time dynamic reconstruction method is accurate in solution, can realize real-time human body dynamic reconstruction, and adapts to high-resolution conditions.

Description

Technical field [0001] The invention relates to the technical field of computer vision and computer graphics, in particular to a method and device for real-time dynamic reconstruction of a human body with high resolution based on a hash table. Background technique [0002] The dynamic 3D reconstruction of the human body is a key issue in the field of computer graphics and computer vision. High-quality three-dimensional human body models have broad application prospects and important application values ​​in the fields of film and television entertainment, demographic data statistics and analysis. However, the acquisition of high-quality human body 3D models usually rely on expensive laser scanners or multi-camera array systems. Although the accuracy is high, there are significant disadvantages: First, the memory occupies a lot, because traditional methods are generally based on A uniformly divided voxel grid is difficult to adapt to high-resolution situations. Second, the speed ...

AI Technical Summary

Problems solved by technology

However, the acquisition of high-quality human body 3D models is usually achieved by expensive laser scanners or multi-camera array systems. Although the accuracy is high, there are also some obvious shortcomings: First, the video memory takes up a lot, because traditional methods are generally based on Evenly divided voxel grid, it is difficult to adapt to high-resolution situations

Second, the speed is slow, and it often takes at least 10 minutes to several hours to reconstruct a 3D human body model

Images