Soccer on Your Tabletop
arXiv:1806.00890
Abstract
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.
arXiv commentCVPR'18. Project: http://grail.cs.washington.edu/projects/soccer/
References in corpus (12)
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Multi-Scale Context Aggregation by Dilated Convolutions
- VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
- Learning from Synthetic Humans
- Stacked Hourglass Networks for Human Pose Estimation
- Convolutional Pose Machines
- Playing for Data: Ground Truth from Computer Games
- Single-Image Depth Perception in the Wild
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation
- General Automatic Human Shape and Motion Capture Using Volumetric Contour Cues