Detailed, Accurate, Human Shape Estimation from Clothed 3D Scan Sequences

Chao Zhang (1) , Sergi Pujades (1) , Michael J Black (1) , Gerard Pons-Moll (1)

1 Max Planck Institute for Intelligent Systems [Tübingen]

We address the problem of estimating human pose and body shape from 3D scans over time. Reliable estimation of 3D body shape is necessary for many applications including virtual try-on, health monitoring, and avatar creation for virtual reality. Scanning bodies in minimal clothing, however, presents a practical barrier to these applications. We address this problem by estimating body shape under clothing from a sequence of 3D scans. Previous methods that have exploited body models produce smooth shapes lacking personalized details. We contribute a new approach to recover a personalized shape of the person. The estimated shape deviates from a parametric model to fit the 3D scans. We demonstrate the method using high quality 4D data as well as sequences of visual hulls extracted from multi-view images. We also make available BUFF, a new 4D dataset that enables quantitative evaluation http://buff.is.tue.mpg.de/. Our method out- performs the state of the art in both pose estimation and shape estimation, qualitatively and quantitatively.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Chao Zhang, Sergi Pujades, Michael J Black, Gerard Pons-Moll. Detailed, Accurate, Human Shape Estimation from Clothed 3D Scan Sequences. CVPR 2017 - IEEE Conference on Computer Vision and Pattern Recognition, Jul 2017, Honolulu, United States. pp.5484-5493, ⟨10.1109/CVPR.2017.582⟩. ⟨hal-02162183⟩