3D Human Body Reconstruction from a Single Image via Volumetric Regression

Aaron S. Jackson, Chris Manafas, and Georgios Tzimiropoulos


This paper proposes the use of an end-to-end Convolutional Neural Network for direct reconstruction of the 3D geometry of humans via volumetric regression. The proposed method does not require the fitting of a shape model and can be trained to work from a variety of input types, whether it be landmarks, images or segmentation masks. Additionally, non-visible parts, either self-occluded or otherwise, are still reconstructed, which is not the case with depth map regression. We present results that show that our method can handle both pose variation and detailed reconstruction given appropriate datasets for training.

Link to paper [arXiv]


  title={{3D Human Body Reconstruction from a Single Image via Volumetric Regression}},
  author={Jackson, Aaron S and Manafas, Chris  and Tzimiropoulos, Georgios},
  booktitle={ECCV Workshop Proceedings},
  series={PeopleCap 2018},


Several Creative Commons licensed images were used in our paper. Attribution is provided in the following list: