We present a novel method for real-time pose and shape reconstruction of two strongly interacting hands. Our approach is the first two-hand tracking solution that combines an extensive list of favorable properties, namely it is marker-less, uses a single consumer-level depth camera, runs in real time, handles inter- and intra-hand collisions, and automatically adjusts to the user's hand shape. In order to achieve this, we embed a recent parametric hand pose and shape model and a dense correspondence predictor based on a deep neural network into a suitable energy minimization framework. For training the correspondence prediction network, we synthesize a two-hand dataset based on physical simulations that includes both hand pose and shape annotations while at the same time avoiding inter-hand penetrations. To achieve real-time rates, we phrase the model fitting in terms of a nonlinear least-squares problem so that the energy can be optimized based on a highly efficient GPU-based Gauss-Newton optimizer. We show state-of-the-art results in scenes that exceed the complexity level demonstrated by previous work, including tight two-hand grasps, significant inter-hand occlusions, and gesture interaction.

@Article\{MDBSVOCT19,
  author       = "Mueller, Franziska and Davis, Micah and Bernard, Florian and Sotnychenko, Oleksandr and Verschoor, Mickeal and Otaduy, Miguel A. and Casas, Dan and Theobalt, Christian",
  title        = "Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera",
  journal      = "ACM Trans. on Graphics (Proc. of ACM SIGGRAPH)",
  number       = "4",
  volume       = "38",
  month        = "july",
  year         = "2019",
  url          = "http://gmrv.es/Publications/2019/MDBSVOCT19"
}