Model-based Outdoor Performance Capture

International Conference on 3D Vision, 3DV 2016


We propose a new model-based method to accurately reconstruct human performances captured outdoors in a multi-camera setup. Starting from a template of the actor model, we introduce a new unified implicit representation for both, articulated skeleton tracking and nonrigid surface shape refinement. Our method fits the template to unsegmented video frames in two stages – first, the coarse skeletal pose is estimated, and subsequently non-rigid surface shape and body pose are jointly refined. Particularly for surface shape refinement we propose a new combination of 3D Gaussians designed to align the projected model with likely silhouette contours without explicit segmentation or edge detection. We obtain reconstructions of much higher quality in outdoor settings than existing methods, and show that we are on par with sate-of-the-art methods on indoor scenes for which they were designed.



    author = {Robertini, Nadia and Casas, Dan and Rhodin, Helge and Seidel, Hans-Peter and Theobalt, Christian}
    title = {Model-based Outdoor Performance Capture},
    booktitle = {Proceedings of the 2016 International Conference on 3D Vision (3DV 2016)},
    year = {2016},
    url = {}


We thank all reviewers for their valuable feedback and The Foundry for license support. This research was funded by the ERC Starting Grant project CapReal (335545).