A Human Shape and Pose Estimation Method for Object Occlusion Scenarios

Abstract

The invention discloses a method for estimating human body shape and posture in an object-occluded scene, converting the calculated weak perspective projection parameters into camera coordinates, and obtaining a UV image containing human body shape information without occlusion; two-dimensional human body The image is occluded by random object pictures, and the human body mask under occlusion is obtained; the obtained virtual occlusion data is trained to encode-decode the structure of the UV map repair network; the real object is input to occlude the color image of the human body, and the mask image is used as the true value to construct A saliency detection network with encoding-decoding structure; use the latent space features obtained by encoding to supervise the human body encoding network training; input the occluded human body color image to obtain a complete UV image; use the corresponding relationship between the UV image and the 3D model of the human body to restore the occlusion situation 3D model of the human body. The invention transforms the shape estimation of the occluded human body into the image restoration problem of the two-dimensional UV map, and then realizes the real-time and dynamic reconstruction of the human body in the occluded scene.

Description

technical field [0001] The invention belongs to the fields of computer vision and three-dimensional vision, and in particular relates to a method for estimating human body shape and posture in an object-occluded scene. Background technique [0002] Estimating the shape and pose of a 3D human body from a single image is a research hotspot in the field of 3D vision in recent years. It plays an important role in the application of virtual reality technology such as human motion capture, virtual fitting and human animation. In recent years, deep learning technology has simplified the solution to restore the overall shape of the human body from a single image. Especially after the SMPL model was proposed and widely used, the 3D human body shape and pose estimation of monocular images has undergone multiple stages of vigorous development. , including (1) optimize and solve SMPL parameters by matching two-dimensional visual features; (2) use convolutional neural network (CNN) to d...

AI Technical Summary

Problems solved by technology

However, most of the existing methods do not consider the common phenomenon of occlusion between people and objects.

Such methods cannot be directly transferred to human estimation in occluded scenarios without explicitly considering occlusion.

This makes them very sensitive to scenes with occlusion or even slight object occlusion, which is difficult to meet the needs of reality

[0003] For a long time, the 3D shape and pose estimation of the human body in occlusion scenes has always been a difficult point in the field. The main reasons are: (1) Object occlusion will introduce serious ambiguity in network training, and lead to a significant reduction in image features that can be directly used , thus affecting the complete 3D human body shape estimation effect

(2) Due to the universality and randomness of occluded objects, it is difficult for the network to accurately segment the pixels where the human body and occluded objects are located in the image, resulting in interference with the reconstruction results

Images