Capture Dense: Markerless Motion Capture Meets Dense Pose Estimation

TL;DR

This paper introduces a unified framework combining markerless motion capture with dense pose estimation, enhancing accuracy and efficiency in human pose analysis and dataset creation.

Contribution

It presents a novel markerless motion capture method leveraging dense pose features and improves dense pose detection using multiview motion capture data.

Findings

Enhanced accuracy over state-of-the-art markerless motion capture methods

Improved dense pose detector performance with multiview data

Public release of dense pose dataset and detector

Abstract

We present a method to combine markerless motion capture and dense pose feature estimation into a single framework. We demonstrate that dense pose information can help for multiview/single-view motion capture, and multiview motion capture can help the collection of a high-quality dataset for training the dense pose detector. Specifically, we first introduce a novel markerless motion capture method that can take advantage of dense parsing capability provided by the dense pose detector. Thanks to the introduced dense human parsing ability, our method is demonstrated much more efficient, and accurate compared with the available state-of-the-art markerless motion capture approach. Second, we improve the performance of available dense pose detector by using multiview markerless motion capture data. Such dataset is beneficial to dense pose training because they are more dense and accurate and consistent, and can compensate for the corner cases such as unusual viewpoints. We quantitatively demonstrate the improved performance of our dense pose detector over the available DensePose. Our dense pose dataset and detector will be made public.