The paper "Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer" by Daniel Kienzle, Robin Sch?n, Rainer Lienhart, and Shin’Ichi Satoh has been accepted to the CVSports Workshop, held in conjunction with the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

?

In this work, the authors present a novel method for analyzing table tennis technique by estimating both the 3D trajectory and the spin of the ball from standard broadcast videos.
A key highlight of the paper is that the model is trained entirely on synthetic, physics-based simulation data.
Thanks to a carefully designed data representation and problem formulation, the approach generalizes effectively to real-world footage without requiring any labeled real data.

?

More paper details are given at? https://kiedani.github.io/CVPRW2025/.

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.