Abstract
Reconstructing 3D human poses from a single 2D image is an ill-posed problem without considering the human body model. Explicitly enforcing physiological constraints is known to be non-convex and usually leads to difficulty in finding an optimal solution. An attractive alterna- tive is to learn a prior model of the human body from a set of human pose data. In this paper, we develop a new approach, namely pose locality con- strained representation (PLCR), to model the 3D human body and use it to improve 3D human pose reconstruction. In this approach, the hu- man pose space is first hierarchically divided into lower-dimensional pose subspaces by subspace clustering. After that, a block-structural pose dic- tionary is constructed by concatenating the basis poses from all the pose subspaces. Finally, PLCR utilizes the block-structural pose dictionary to explicitly encourage pose locality in human-body modeling – nonzero co- efficients are only assigned to the basis poses from a small number of pose subspaces that are close to each other in the pose-subspace hierarchy. We combine PLCR into the matching-pursuit based 3D human-pose recon- struction algorithm and show that the proposed PLCR-based algorithm outperforms the state-of-the-art algorithm that uses the standard sparse representation and physiological regularity in reconstructing a variety of human poses from both synthetic data and real images.