Capture Dense: Markerless Motion Capture Meets Dense Pose Estimation
This work addresses the challenge of improving human motion analysis for applications like animation and robotics by combining two complementary techniques, though it is incremental in nature.
The paper tackles the problem of integrating markerless motion capture with dense pose estimation, showing that dense pose information improves motion capture efficiency and accuracy, while multiview motion capture data enhances dense pose detector performance, with quantitative improvements over existing methods.
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.