# DeepMoCap: Deep Optical Motion Capture Using Multiple Depth Sensors and Retro-Reflectors

arXiv: https://arxiv.org/abs/2110.07283 · HTML: https://mlsanity.com/paper/2110.07283/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 56 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 22 of 22)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies](https://mlsanity.com/paper/1801.01615/) (2018)
- [Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose](https://mlsanity.com/paper/1611.07828/) (2016)
- [VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera](https://mlsanity.com/paper/1705.01583/) (2017)
- [Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs](https://mlsanity.com/paper/1703.08014/) (2017)
- [DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model](https://mlsanity.com/paper/1605.03170/) (2016)
- [Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image](https://mlsanity.com/paper/1701.00295/) (2017)
- [Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos](https://mlsanity.com/paper/1703.10898/) (2017)
- [MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild](https://mlsanity.com/paper/1607.02046/) (2016)
- [MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior](https://mlsanity.com/paper/1701.02354/) (2017)
- [3D Human Pose Estimation in RGBD Images for Robotic Task Learning](https://mlsanity.com/paper/1803.02622/) (2018)
- [LSTM Pose Machines](https://mlsanity.com/paper/1712.06316/) (2017)
- [Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networks](https://mlsanity.com/paper/1702.08652/) (2017)
- [Deep Affordance-grounded Sensorimotor Object Recognition](https://mlsanity.com/paper/1704.02787/) (2017)
- [An Integrated Platform for Live 3D Human Reconstruction and Motion Capturing](https://mlsanity.com/paper/1712.03084/) (2017)
- [Real-time marker-less multi-person 3D pose estimation in RGB-Depth camera networks](https://mlsanity.com/paper/1710.06235/) (2017)
- [Real-Time Human Motion Capture with Multiple Depth Cameras](https://mlsanity.com/paper/1605.08068/) (2016)

## Abstract (arXiv)

In this paper, a marker-based, single-person optical motion capture method (DeepMoCap) is proposed using multiple spatio-temporally aligned infrared-depth sensors and retro-reflective straps and patches (reflectors). DeepMoCap explores motion capture by automatically localizing and labeling reflectors on depth images and, subsequently, on 3D space. Introducing a non-parametric representation to encode the temporal correlation among pairs of colorized depthmaps and 3D optical flow frames, a multi-stage Fully Convolutional Network (FCN) architecture is proposed to jointly learn reflector locations and their temporal dependency among sequential frames. The extracted reflector 2D locations are spatially mapped in 3D space, resulting in robust 3D optical data extraction. The subject's motion is efficiently captured by applying a template-based fitting technique on the extracted optical data. Two datasets have been created and made publicly available for evaluation purposes; one comprising multi-view depth and 3D optical flow annotated images (DMC2.5D), and a second, consisting of spatio-temporally aligned multi-view depth images along with skeleton, inertial and ground truth MoCap data (DMC3D). The FCN model outperforms its competitors on the DMC2.5D dataset using 2D Percentage of Correct Keypoints (PCK) metric, while the motion capture outcome is evaluated against RGB-D and inertial data fusion approaches on DMC3D, outperforming the next best method by 4.5% in total 3D PCK accuracy.