Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras

By Ahmed Elhayek, Edilson de Aguiar, Arjun Jain, Jonathan Tompson, Leonid Pishchulin, Mykhaylo Andriluka, C. Bregler, Bernt Schiele, Christian Theobalt. 2015

162 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

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

In Control and Systems Engineering

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “To address these problems, algorithms were also studied to construct human skeleton models directly from the multi-images without calculating the depth image [71], [72], [73].”
Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry (2019, background): “More recently, many researchers [11, 10] used deep neural networks to model multi-view input with full 3D supervision.”
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies (2018, methodology): “The standard pipeline is based on a multiview camera setup and tracking with a 3D template model [33, 25, 17, 12, 30, 18, 55, 13, 47, 19, 21].”
Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes: The Importance of Multiple Scene Constraints (2018, background): “Systems designed for the 3d reconstruction of multiple people are relatively rare and existing ones are based on multiple cameras [1, 6, 5, 12, 14].”
Unite the People: Closing the Loop Between 3D and 2D Human Representations (2017, background): “Recent approaches target 3D pose ground truth from natural scenes, but either rely on vision systems prone to failure [11] or inertial suits that modify the appearance of the body and are prone to motion drift [44].”
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2016, background): “With the growing availability of large datasets and the advent of Deep Learning, the emphasis has shifted towards using discriminative 2D pose regressors [11, 13, 15, 16, 24, 27, 32, 43, 47, 48, 66, 70, 71] to extract the 2D pose and infer a 3D one from it [9, 19, 72, 76].”
Soccer on Your Tabletop (2018, methodology): “[33] uses a CNN person segmentation per camera and fuses the estimations in 3D. Body pose estimation from multiple cameras is used for outdoor motion capture in [41, 11].”
Panoptic Studio: A Massively Multiview System for Social Interaction Capture (2016, methodology): “A few methods facilitate body pose detectors in multiple views to reconstruct 3D body poses [46], [47], [48], [49], [50].”
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose (2016, background): “, [12, 31, 4, 11]), it is interesting to note that the representation of 3D human pose in a discretized 3D space has also been previously adopted in multi-view settings [7, 15, 23], where it was used to accommodate predictions from different viewpoints.”
A Review of the Evolution of Vision-Based Motion Analysis and the Integration of Advanced Computer Vision Methods Towards Developing a Markerless System (2018, methodology): “Researchers have attempted to address this situation using improved searching algorithms [92], extra information derived from robust body part detectors [90] and Fig.”
Monocular 3D Human Pose Estimation Using Transfer Learning and Improved CNN Supervision (2016, background): “Combinig discriminative and generative methods yields increased robustness outdoors [70, 67, 3, 8, 21, 55, 56, 11].”