Abstract
Three-dimensional human shape reconstruction is important in many applications, such as virtual or augmented reality (VR/AR), virtual clothing fitting, and healthcare. In this paper, we propose a learning-based method for reconstructing a whole-body point cloud from a single front-view human-depth image. Because actual depth images typically suffer from noise and missing data, an accurate point cloud cannot be reasonably obtained by simply predicting a back-view depth image. To solve this problem, we propose to use convolutional neural networks that not only predict a back-view depth image but also refine the input front-view depth image. To train the networks, we propose a carefully designed method for generating synthetic but realistic human-depth images with noise and missing data. Experiments show that the proposed method is effective for obtaining seamless whole-body point clouds. In addition, the experiments show that the networks trained on the synthetic depth images are ready for application to actual depth images.
Highlights
3D human shape reconstruction plays a central role in many applications, such as virtual or augmented reality (VR/AR), virtual clothes fitting, and healthcare
3D human shape reconstruction plays a central role in many applications, such as VR/AR, virtual clothes fitting, and healthcare
Our experiments show that the networks trained with our realistic training data are more effective for obtaining accurate whole-body point clouds from actual depth images
Summary
3D human shape reconstruction plays a central role in many applications, such as VR/AR, virtual clothes fitting, and healthcare. To acquire a 3D human shape model, one can use an active 3D scanner [1], a multi-camera system [2], several RGB-depth (RGB-D) cameras [3]–[6], or a single color or RGB-D camera [7]–[36]. Among these options, a single RGB-D camera has the advantage of no depth ambiguity, which is a fundamental problem when using a single color camera. An RGB-D camera can be installed in narrow places as as a color camera
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have