Physics-Guided Human Motion Capture with Pose Probability Modeling

Authors: Jingyi Ju, Buzhen Huang, Chen Zhu, Zhihao Li, Yangang Wang

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results show that our method outperforms previous physics-based methods in both joint accuracy and success rate.
Researcher Affiliation Collaboration Jingyi Ju1,2 , Buzhen Huang1,2 , Chen Zhu1,2 , Zhihao Li3 and Yangang Wang1,2 1Southeast University 2Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Nanjing, China 3Huawei Noah s Ark Lab {jingyiju, hbz, yangangwang}@seu.edu.cn, zc1213856@163.com, zhihao.li@huawei.com
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes More information can be found at https://github. com/Me-Ditto/Physics-Guided-Mocap.
Open Datasets Yes Human3.6M [Ionescu et al., 2013] is an indoor dataset for human motion capture... 3DOH [Zhang et al., 2020] is the first dataset to handle the object occluded human body estimation... MPI-INF-3DHP [Mehta et al., 2017] is a single-person 3D pose dataset.
Dataset Splits Yes Following previous works [Yuan et al., 2021; Shimada et al., 2020], we use 2 subjects (S9, S11) for evaluation, and the others are used for training.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper mentions 'Mu Jo Co' and 'SMPL model' but does not provide specific version numbers for these or other key software components or libraries.
Experiment Setup No The paper describes the overall training procedure and loss functions used, but does not provide specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, number of epochs) or optimizer settings.