@inproceedings{tan2020self-supervised,
author = {Tan, Feitong and Zhu, Hao and Cui, Zhaopeng and Zhu, Siyu and Pollefeys, Marc and Tan, Ping},
title = {Self-Supervised Human Depth Estimation From Monocular Videos},
booktitle = {CVPR 2020},
year = {2020},
month = {June},
abstract = {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.},
url = {http://approjects.co.za/?big=en-us/research/publication/self-supervised-human-depth-estimation-from-monocular-videos/},
}