Previous methods on estimating detailed human depth often require supervised training with `ground truth' depth data. This paper presents a self-supervised method that can be trained on YouTube videos without known depth, which makes training data collection simple and improves the generalization of the learned network. The self-supervised learning is achieved by minimizing a photo-consistency loss, which is evaluated between a video frame and its neighboring frames warped according to the estimated depth and the 3D non-rigid motion of the human body. To solve this non-rigid motion, we first estimate a rough SMPL model at each video frame and compute the non-rigid body motion accordingly, which enables self-supervised learning on estimating the shape details. Experiments demonstrate that our method enjoys better generalization and performs much better on data in the wild.
@article{arxiv.2005.03358,
title = {Self-Supervised Human Depth Estimation from Monocular Videos},
author = {Feitong Tan and Hao Zhu and Zhaopeng Cui and Siyu Zhu and Marc Pollefeys and Ping Tan},
journal= {arXiv preprint arXiv:2005.03358},
year = {2020}
}
Comments
Accepted by IEEE Conference on Computer Vision and Patten Recognition (CVPR), 2020