Soccer on Your Tabletop
This enables interactive viewing of soccer games in 3D or AR, but is incremental as it builds on existing depth estimation techniques.
The paper tackles the problem of creating interactive 3D reconstructions from monocular soccer videos by estimating player depth maps using a CNN trained on 3D data from video games, achieving results comparable to state-of-the-art methods on synthetic and real footage.
We present a system that transforms a monocular video of a soccer game into a moving 3D reconstruction, in which the players and field can be rendered interactively with a 3D viewer or through an Augmented Reality device. At the heart of our paper is an approach to estimate the depth map of each player, using a CNN that is trained on 3D player data extracted from soccer video games. We compare with state of the art body pose and depth estimation techniques, and show results on both synthetic ground truth benchmarks, and real YouTube soccer footage.