Three-dimensional human body reconstruction method and device, electronic equipment and storage medium

Abstract

The invention discloses a three-dimensional human body reconstruction method and apparatus, electronic equipment and a storage medium. The method comprises the steps of obtaining a human body image; inputting the human body image into the trained three-dimensional human body reconstruction model to obtain a three-dimensional reconstruction result of the human body image, wherein the trained three-dimensional human body reconstruction model is obtained by training images generated by rendering a human body scanning model after human body scanning into different background images. According to the invention, the global features and the local features of the point cloud are extracted to provide semantic information and strong constraint for the point cloud, so that the three-dimensional human body reconstruction model can learn global attitude information and local detail information; and three-dimensional semantic features are obtained through the parameterized human body model. Strong constraint is provided for the model, the accuracy and trueness of details of the three-dimensional human body reconstruction model are improved, and meanwhile, the robustness of human body postures is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method, device, electronic equipment and storage medium for three-dimensional human body reconstruction. Background technique [0002] At present, 3D human body reconstruction is widely used in virtual reality, game experience, virtual try-on and other fields. [0003] In the 3D human body reconstruction model, the implicit expression method based on pixel alignment is dominant. This method implicitly represents the 3D human body as an occupancy field in 3D space, and aligns the points sampled in 3D space with the 2D image. Whether it is inside the human body occupancy field, on the one hand, this method ignores the spatial geometric dependence between points, resulting in local reconstruction details such as clothes folds, facial wrinkles, etc. are not realistic enough. On the other hand, existing methods are less robust to human poses due to factors such as scene diversity...

AI Technical Summary

Problems solved by technology

[0003] In the 3D human body reconstruction model, the implicit expression method based on pixel alignment is dominant. This method implicitly represents the 3D human body as an occupancy field in 3D space, and aligns the points sampled in 3D space with the 2D image. Whether it is inside the human body occupancy field, on the one hand, this method ignores the spatial geometric dependence between points, resulting in local reconstruction details such as clothes folds, facial wrinkles, etc. are not realistic enough

On the other hand, existing methods are less robust to human poses due to factors such as scene diversity and complexity of human poses.

Images