Reconstructing NBA Players

Luyang Zhu   Konstantinos Rematas   Brian Curless   Steve Seitz   Ira Kemelmacher-Shlizerman
University of Washington    

Proceedings of the European Conference on Computer Vision (ECCV), 2020


Great progress has been made in 3D body pose and shape estimation from a single photo. Yet, state-of-the-art results still suffer from errors due to challenging body poses, modeling clothing, and self occlusions. The domain of basketball games is particularly challenging, as it exhibits all of these challenges. In this paper, we introduce a new approach for reconstruction of basketball players that outperforms the state-of-the-art. Key to our approach is a new method for creating poseable, skinned models of NBA players, and a large database of meshes (derived from the NBA2K19 video game), that we are releasing to the research community. Based on these models, we introduce a new method that takes as input a single photo of a clothed player in any basketball pose and outputs a high resolution mesh and 3D pose for that player. We demonstrate substantial improvement over state-of-the-art, single-image methods for body shape reconstruction.


Paper pdf

    author={Zhu, Luyang and Rematas, Konstantinos and Curless, Brian and Seitz, Steve and Kemelmacher-Shlizerman, Ira},
    title={Reconstructing NBA players},
    booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
    month = {August},

Code and Dataset

NBA2K Dataset


This work is supported by NSF/Intel Visual and Experimental Computing Award #1538618 and the UW Reality Lab funding from Facebook, Google and Futurewei. We thank Visual Concepts for allowing us to capture, process, and share our extracted NBA2K19 data for research. We thank all of the photo owners for allowing us to use their photos.


Luyang Zhu