Shielding three-dimensional human body reconstruction method based on depth map restoration

Abstract

The invention relates to a method for reconstructing a three-dimensional human body with shielding based on depth map restoration, which is used for solving the problem of restoring the posture, the body shape and the surface details of a three-dimensional human body model from a single RGB human body image containing a shielding object. The method comprises the following steps: a basic model construction stage: constructing a basic three-dimensional human body model through an existing SMPL model construction method; a body shape posture optimization stage: optimizing three-dimensional human body joint point positions through a Joint encoder network, and optimizing three-dimensional human body shape characteristics through an Anchor encoder network; a surface detail optimization stage: providing a DHDNet network structure, and recovering three-dimensional human body surface details by reconstructing a complete human body depth image. Meanwhile, a DepthHuman data set containing a large number of human body RGB images and synthesized human body depth images is constructed. The effect of reconstructing the complete three-dimensional human body model containing rich details only through the single RGB human body image containing the shielding object is achieved.

Description

Technical field: [0001] The present invention relates to the field of computer image processing and computer graphics, in particular to a single-vision with occlusion based on depth map restoration Figure three Human body reconstruction method. Background technique: [0002] In recent years, the 3D human body reconstruction technology of the monocular camera has been a very hot topic. This technology has a wide range of application scenarios in the VR / AR field, such as VR dress-up, VR chat rooms, etc. At the same time, it also has great application prospects in the fields of film and television production and game development. existing single vision Figure three The three-dimensional human body reconstruction technology has the problem that the reconstructed model lacks details, and the texture information of the human body surface in the occluded area is completely lost. This makes it impossible to reconstruct a complete 3D human body model with rich details from an inpu...

AI Technical Summary

Problems solved by technology

[0004] In summary, the existing single-vision Figure three Most of the models obtained by the three-dimensional human body reconstruction method lack surface details, and the existing methods do not consider the presence of occluders in the input image, which are very common in practical application scenarios

Images