# Using Learnable Physics for Real-Time Exercise Form Recommendations

arXiv: https://arxiv.org/abs/2310.07221 · HTML: https://mlsanity.com/paper/2310.07221/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 37 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 8 of 8)

- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay](https://mlsanity.com/paper/1803.09820/) (2018)
- [BlazePose: On-device Real-time Body Pose tracking](https://mlsanity.com/paper/2006.10204/) (2020)
- [Pose Trainer: Correcting Exercise Posture using Pose Estimation](https://mlsanity.com/paper/2006.11718/) (2020)
- [Recognizing Exercises and Counting Repetitions in Real Time](https://mlsanity.com/paper/2005.03194/) (2020)
- [Muscle Vision: Real Time Keypoint Based Pose Classification of Physical Exercises](https://mlsanity.com/paper/2203.12111/) (2022)

## Built on by (most cited first, 4 of 4)

- [Benchmarking Reliability of Deep Learning Models for Pathological Gait Classification](https://mlsanity.com/paper/2409.13643/) (2024)
- [Real-Time Feedback and Benchmark Dataset for Isometric Pose Evaluation](https://mlsanity.com/paper/2506.11774/) (2025)
- [(LiFT) Lightweight Fitness Transformer: A language-vision model for Remote Monitoring of Physical Training](https://mlsanity.com/paper/2506.06480/) (2025)
- [Posture-Driven Action Intent Inference for Playing style and Fatigue Assessment](https://mlsanity.com/paper/2507.11642/) (2025)

## Abstract (arXiv)

Good posture and form are essential for safe and productive exercising. Even in gym settings, trainers may not be readily available for feedback. Rehabilitation therapies and fitness workouts can thus benefit from recommender systems that provide real-time evaluation. In this paper, we present an algorithmic pipeline that can diagnose problems in exercise techniques and offer corrective recommendations, with high sensitivity and specificity in real-time. We use MediaPipe for pose recognition, count repetitions using peak-prominence detection, and use a learnable physics simulator to track motion evolution for each exercise. A test video is diagnosed based on deviations from the prototypical learned motion using statistical learning. The system is evaluated on six full and upper body exercises. These real-time recommendations, counseled via low-cost equipment like smartphones, will allow exercisers to rectify potential mistakes making self-practice feasible while reducing the risk of workout injuries.