@inproceedings{12eb1d1fc47546c487ee928f3d739024,
title = "Towards accurate marker-less human shape and pose estimation over time",
abstract = "Existing markerless motion capture methods often assume known backgrounds, static cameras, and sequence specific motion priors, limiting their application scenarios. Here we present a fully automatic method that, given multi-view videos, estimates 3D human pose and body shape. We take the recently proposed SMPLify method \cite{bogo2016keep} as the base method and extend it in several ways. First we fit a 3D human body model to 2D features detected in multi-view images. Second, we use a CNN method to segment the person in each image and fit the 3D body model to the contours, further improving accuracy. Third we utilize a generic and robust DCT temporal prior to handle the left and right side swapping issue sometimes introduced by the 2D pose estimator. Validation on standard benchmarks shows our results are comparable to the state of the art and also provide a realistic 3D shape avatar. We also demonstrate accurate results on HumanEva and on challenging monocular sequences of dancing from YouTube.",
keywords = "3D-reconstruction, Body-model, Marker-less, Multi-view, Shape-And-pose-estimation",
author = "Yinghao Huang and Federica Bogo and Christoph Lassner and Angjoo Kanazawa and Gehler, {Peter V.} and Javier Romero and Ijaz Akhter and Black, {Michael J.}",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 7th IEEE International Conference on 3D Vision, 3DV 2017 ; Conference date: 10-10-2017 Through 12-10-2017",
year = "2018",
month = may,
day = "25",
doi = "10.1109/3DV.2017.00055",
language = "English",
series = "Proceedings - 2017 International Conference on 3D Vision, 3DV 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "421--430",
booktitle = "Proceedings - 2017 International Conference on 3D Vision, 3DV 2017",
address = "United States",
}