Dynamic Surface Function Networks
for Clothed Human Bodies

Andrei Burov      Matthias Nießner      Justus Thies     

Technical University of Munich


We present a novel method for temporal coherent reconstruction and tracking of clothed humans. Given a monocular RGB-D sequence, we learn a person-specific body model which is based on a dynamic surface function network. To this end, we explicitly model the surface of the person using a multi-layer perceptron (MLP) which is embedded into the canonical space of the SMPL body model. With classical forward rendering, the represented surface can be rasterized using the topology of a template mesh. For each surface point of the template mesh, the MLP is evaluated to predict the actual surface location. To handle pose-dependent deformations, the MLP is conditioned on the SMPL pose parameters. We show that this surface representation as well as the pose parameters can be learned in a self-supervised fashion using the principle of analysis-by-synthesis and differentiable rasterization. As a result, we are able to reconstruct a temporally coherent mesh sequence from the input data. The underlying surface representation can be used to synthesize new animations of the reconstructed person including pose-dependent deformations.



[Paper] [Arxiv] [GitHub]
If you find our work useful, please consider citing it:
      title={Dynamic Surface Function Networks for Clothed Human Bodies}, 
      author={Andrei Burov and Matthias Nie{\ss}ner and Justus Thies},


If you would like to access our sequences, please contact us directly by email: andrei.burov at tum.de