从单视角直播视频推断乒乓球旋转与轨迹，无需真实标注数据。
Towards Ball Spin and Trajectory Analysis in Table Tennis Broadcast Videos via Physically Grounded Synthetic-to-Real Transfer
- 用合成数据训练神经网络，输入为2D轨迹，输出3D轨迹和初始旋转。
- 在无真实标签情况下实现92.0%旋转分类准确率，2D重投影误差仅0.19%图像对角线。
- 物理合理的合成数据+针对性增强，让模型自然泛化到真实视频，适合体育分析研究者。
分析乒乓球运动员技术需掌握球的三维轨迹与旋转信息。由于旋转无法直接从标准广播视频中获取，本文证明可通过视频中球的轨迹间接推断旋转。提出一种新方法，从视频中的二维轨迹推断出球的初始旋转和三维轨迹。在缺乏广播视频真实标签的情况下，仅使用合成数据训练神经网络。得益于输入表示设计、物理正确的合成数据及针对性增强策略，该网络可自然泛化至真实数据。值得注意的是，这些简单技术已足以实现良好泛化，完全无需真实数据参与训练。据我们所知，这是首个针对单目广播视频实现旋转与轨迹预测的方法，在旋转分类上达到92.0%准确率，2D重投影误差为图像对角线的0.19%。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。