Soccer on Your Tabletop
By Konstantinos Rematas, Ira Kemelmacher-Shlizerman, Brian Curless, S. M. Seitz. 2018
100 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Jitendra Malik
- Ming-Hsuan Yang
- Dacheng Tao
- Andrea Vedaldi
- Trevor Darrell
- Andrew Zisserman
- Xiaogang Wang
Citations in the corpus
- Stochastic Prediction of Multi-Agent Interactions from Partial Observations (2019, background): “…exist (e.g., based on wearable sensors (Sanguesa, 2017), multiple calibrated cameras (Manafifard et al., 2017), or complex monocular vision pipelines (Rematas et al., 2018)), we are interested in seeing how far we can get with a pure learning based approach, since such a method will be more…”
- Clear Grasp: 3D Shape Estimation of Transparent Objects for Manipulation (2019, methodology): “Synthetic data has proven to be useful in various tasks such as depth estimation [41], 3D semantic scene completion [44], hand pose estimation”
- Learning the Depths of Moving People by Watching Frozen People (2019, methodology): “[30] predict depth of moving soccer players using synthetic training data from FIFA video games.”
- Deep 3D human pose estimation: A review (2021, unknown): “Thus, human pose estimation can be used to evaluate and educate people in various forms of sports such as swimming (Zecha et al., 2018), Tai Chi (Scott et al., 2017), soccer (Rematas et al., 2018).”
- Synthetic Data for Deep Learning (2019, background): “in a very interesting application of pose estimation called “Soccer on Your Tabletop” [486].”