PulseAugur
EN
LIVE 10:39:22

New method boosts AI pose estimation for extreme gymnastics

By PulseAugur Editorial · [1 sources] ·

Researchers have developed a method to improve human pose estimation for trampoline gymnastics, a sport characterized by extreme poses and unusual viewpoints. By fine-tuning the ViTPose model with a combination of real extreme poses and synthetic data generated from motion capture recordings, they achieved significant accuracy improvements. This approach bridges the performance gap for challenging poses, reducing mean per joint position error (MPJPE) by 42.7% in 3D. AI

IMPACT Enhances AI's ability to analyze complex human movements, potentially aiding sports analytics and performance training.

RANK_REASON The cluster contains an academic paper detailing a new method for improving AI performance on a specific task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New method boosts AI pose estimation for extreme gymnastics

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · L\'ea Drolet-Roy, Victor Nogues, B\'erenger Chedal-Anglay, Sylvain Gaudet, Eve Charbonneau, Micka\"el Begon, Lama S\'eoud ·

    Human Pose Estimation in Trampoline Gymnastics: How to Improve Performance on Extreme Poses

    arXiv:2604.01322v2 Announce Type: replace Abstract: Trampoline gymnastics involves extreme human poses and uncommon viewpoints, on which state-of-the art pose estimation models tend to under-perform. We demonstrate that this problem can be addressed by fine-tuning a pose estimati…

RELATED ENTITIES

RELATED TOPICS