Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916710234193920 |
|---|---|
| author | Kienzle, Daniel Schön, Robin Lienhart, Rainer Satoh, Shin'Ichi |
| author_facet | Kienzle, Daniel Schön, Robin Lienhart, Rainer Satoh, Shin'Ichi |
| contents | Analyzing a player's technique in table tennis requires knowledge of the ball's 3D trajectory and spin. While, the spin is not directly observable in standard broadcasting videos, we show that it can be inferred from the ball's trajectory in the video. We present a novel method to infer the initial spin and 3D trajectory from the corresponding 2D trajectory in a video. Without ground truth labels for broadcast videos, we train a neural network solely on synthetic data. Due to the choice of our input data representation, physically correct synthetic training data, and using targeted augmentations, the network naturally generalizes to real data. Notably, these simple techniques are sufficient to achieve generalization. No real data at all is required for training. To the best of our knowledge, we are the first to present a method for spin and trajectory prediction in simple monocular broadcast videos, achieving an accuracy of 92.0% in spin classification and a 2D reprojection error of 0.19% of the image diagonal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19863 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer Kienzle, Daniel Schön, Robin Lienhart, Rainer Satoh, Shin'Ichi Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Analyzing a player's technique in table tennis requires knowledge of the ball's 3D trajectory and spin. While, the spin is not directly observable in standard broadcasting videos, we show that it can be inferred from the ball's trajectory in the video. We present a novel method to infer the initial spin and 3D trajectory from the corresponding 2D trajectory in a video. Without ground truth labels for broadcast videos, we train a neural network solely on synthetic data. Due to the choice of our input data representation, physically correct synthetic training data, and using targeted augmentations, the network naturally generalizes to real data. Notably, these simple techniques are sufficient to achieve generalization. No real data at all is required for training. To the best of our knowledge, we are the first to present a method for spin and trajectory prediction in simple monocular broadcast videos, achieving an accuracy of 92.0% in spin classification and a 2D reprojection error of 0.19% of the image diagonal. |
| title | Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.19863 |