Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images
This work addresses the problem of accurate 3D human pose and shape reconstruction for applications like computer vision and animation, but it is incremental as it builds on existing SMPL-based methods with multi-view inputs.
The paper tackles 3D human body mesh reconstruction from multi-view images using a neural network in the SMPL subspace, reducing projection ambiguity and improving accuracy under clothing, with experiments showing it outperforms existing methods on real-world images, particularly in shape estimations.
We propose a scalable neural network framework to reconstruct the 3D mesh of a human body from multi-view images, in the subspace of the SMPL model. Use of multi-view images can significantly reduce the projection ambiguity of the problem, increasing the reconstruction accuracy of the 3D human body under clothing. Our experiments show that this method benefits from the synthetic dataset generated from our pipeline since it has good flexibility of variable control and can provide ground-truth for validation. Our method outperforms existing methods on real-world images, especially on shape estimations.