Markerless motion capture of interacting characters using multi-view image segmentation

By Yebin Liu, Carsten Stoll, Juergen Gall, Hans-Peter Seidel, Christian Theobalt. 2011

164 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “[73], which uses a modified global optimization method to handle occlusions.”
Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors (2021, methodology): “Although high-end volumetric capture systems [4, 13, 25, 5, 27, 36] based on dense camera rigs (up to 100 cameras [8]) and custom-designed lighting conditions [47, 14] can achieve high-quality reconstruction, they all suffer from complicated system setups and are limited to professional studio…”
Human Shape and Pose Tracking Using Keyframes (2014, unknown): “Average silhouette overlap error of WalkChair ( WlkChr. ), and HammerTable ( HmmrTbl .) from different approaches.”
Two-person interaction detection using body-pose features and multiple instance learning (2012, background): “There are some datasets for pose estimation [33, 17], containing some human-human interaction sequences with videos and synchronized motion capture data.”
Deep Volumetric Video From Very Sparse Multi-view Performance Capture (2018, methodology): “Additional improvements have been proposed using kinematic skeletons [26, 27], segmentation of moving subjects [28–30, 27, 31, 32] and human parametric models [33–39], even enabling single-view reconstruction [40– 44].”
Free-Viewpoint Video of Human Actors Using Multiple Handheld Kinects (2013, methodology): “The state of the art can also handle fast moving character [33] and multiple closely interacting people [18], [19].”
GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models (2020, unknown): “Many image and video-based pose and shape estimation methods have also been proposed[33, 27, 25, 40, 22, 1, 12, 26, 34, 23].”
DoubleFusion: Real-Time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor (2018, methodology): “Liu et al. [23] extended the method to handle multiple interacting performers.”
Motion Capture of Hands in Action Using Discriminative Salient Points (2012, background): “In [25], the motion of two interacting characters is captured.”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, methodology): “For instance, a review on viewinvariant pose representation and estimation is offered by Ji and Liu [32].”