Reconstructing 3D Human Pose by Watching Humans in the Mirror
This addresses the problem of depth ambiguity in single-view 3D pose estimation for computer vision researchers, offering an incremental improvement by leveraging mirror reflections.
The paper tackles 3D human pose reconstruction from a single image with a mirror reflection by introducing an optimization-based method that uses mirror symmetry to resolve depth ambiguity, and it shows that training on their new Mirrored-Human dataset improves existing estimators' accuracy and generalizability.
In this paper, we introduce the new task of reconstructing 3D human pose from a single image in which we can see the person and the person's image through a mirror. Compared to general scenarios of 3D pose estimation from a single view, the mirror reflection provides an additional view for resolving the depth ambiguity. We develop an optimization-based approach that exploits mirror symmetry constraints for accurate 3D pose reconstruction. We also provide a method to estimate the surface normal of the mirror from vanishing points in the single image. To validate the proposed approach, we collect a large-scale dataset named Mirrored-Human, which covers a large variety of human subjects, poses and backgrounds. The experiments demonstrate that, when trained on Mirrored-Human with our reconstructed 3D poses as pseudo ground-truth, the accuracy and generalizability of existing single-view 3D pose estimators can be largely improved.