Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning

October 2019

Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning

Authors:

C. Wang, C. Kong, and S. Lucey
Conference Paper
Proceedings of (ICCV) International Conference on Computer Vision

Abstract:

We propose to learn a 3D pose estimator by distilling knowledge from Non-Rigid Structure from Motion (NRSfM). Our method uses solely 2D landmark annotations. No 3D data, multi-view/temporal footage, or object specific prior is required. This alleviates the data bottleneck, which is one of the major concern for supervised methods. The challenge for using NRSfM as teacher is that they often make poor depth reconstruction when the 2D projections have strong ambiguity. Directly using those wrong depth as hard target would negatively impact the student. Instead, we propose a novel loss that ties depth prediction to the cost function used in NRSfM. This gives the student pose estimator freedom to reduce depth error by associating with image features. Validated on H3.6M dataset, our learned 3D pose estimation network achieves more accurate reconstruction compared to NRSfM methods. It also outperforms other weakly supervised methods, in spite of using significantly less supervision.
@conference{Wang-2019-121009,
author = {C. Wang And C. Kong And S. Lucey},
title = {Distill Knowledge from NRSfM for Weakly Supervised 3D Pose Learning},
booktitle = {Proceedings of (ICCV) International Conference on Computer Vision},
year = {2019},
month = {October},
pages = {743 - 752},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.