WO2025056928 - MACHINE LEARNING SYSTEM FOR MARKER-BASED MOTION CAPTURE
National phase entry is expected:
Publication Number
WO/2025/056928
Publication Date
20.03.2025
International Application No.
PCT/GR2024/000026
International Filing Date
09.09.2024
Title **
[English]
MACHINE LEARNING SYSTEM FOR MARKER-BASED MOTION CAPTURE
[French]
SYSTÈME D'APPRENTISSAGE AUTOMATIQUE POUR CAPTURE DE MOUVEMENTS BASÉE SUR DES MARQUEURS
Applicants **
MOVERSE P.C.
Inventors
ZIOULIS, Nikolaos
THERMOS, Spyridon
CHATZITOFIS, Anargyros
ALMPANIS, Georgios
Priority Data
20230100727
11.09.2023
GR
Application details
| Total Number of Claims/PCT | * |
| Number of Independent Claims | * |
| Number of Priorities | * |
| Number of Multi-Dependent Claims | * |
| Number of Drawings | * |
| Pages for Publication | * |
| Number of Pages with Drawings | * |
| Pages of Specification | * |
| * | |
| Number of Office Actions | * |
| * | |
International Searching Authority |
EPO
* |
| Recordal of a Change of the Applicant's Name/Address |
Change of Applicant's Name and Address
* |
| Type of Assignment |
The Standard Agent's Assignment
* |
| Applicant's Legal Status |
Legal Entity
* |
| * | |
| * | |
| * | |
| * | |
| * | |
| Entry into National Phase under |
Chapter I
* |
| Patent Delivery |
Send the Letters Patent by Courier
* |
| Translation |
|
* The data is based on automatic recognition. Please verify and amend if necessary.
** IP-Coster compiles data from publicly available sources. If this data includes your personal information, you can contact us to request its removal.
Quotation for National Phase entry
| Country | Stages | Total | |
|---|---|---|---|
| China | Filing, Examination, Granting | 3248 | |
| EPO | Filing, Examination, Granting | 25829 | |
| Japan | Filing, Examination, Granting | 3172 | |
| South Korea | Filing, Examination, Granting | 4133 | |
| USA | Filing, Examination, Granting | 10940 |
Total:
47,322
The term for entry into the National Phase has expired. This quotation is for informational purposes only
Contact Us
Abstract[English]
The invention comprises a machine learning-based optical system and methods for performing motion capture. The system comprises an optical sensor setup that provides raw, unstructured landmark inputs and relies on a neural network, trained for balanced regression, to denoise, label and complete them, estimating a richer set of refined landmark positions. The system and methods automatically calibrates the captured subject, and automatically refines the captured motions, improving the naturalism, smoothness and correcting capturing artifacts. The system and methods benefit from a balanced regression training scheme to improve said neural network's performance on long-tailed motion datasets.[French]
L'invention comprend un système optique basé sur l'apprentissage automatique et des procédés destinés à effectuer une capture de mouvements. Le système comprend une installation de capteurs optiques qui fournit en entrée des positions de marqueurs brutes, non structurées et utilise un réseau neuronal, entraîné pour effectuer une régression équilibrée, pour les débruiter, les étiqueter et les compléter, afin d'estimer un ensemble plus riche de positions de marqueurs affinées. Le système et les procédés étalonnent automatiquement le sujet capturé, et affinent automatiquement les mouvements capturés, pour les rendre plus naturels, réguliers, et corriger des artefacts de capture. Le système et les procédés utilisent un schéma d'apprentissage basé sur une régression équilibrée afin d'améliorer les performances dudit réseau neuronal sur des ensembles de données de mouvements à longue queue.