MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction
Authors: Yitao Zhu, Sheng Wang, Mengjie Xu, Zixu Zhuang, Zhixin Wang, Kaidong Wang, Han Zhang, Qian Wang
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In our experiments, we demonstrate the effectiveness and robustness of our proposed MUC method for calibration-free multi-view fusion. ... The results are presented in Table 1. ... We further perform two quantitative ablation studies experiments to objectively measure the effectiveness of the JRN and SRN |
| Researcher Affiliation | Collaboration | 1School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, Shanghai Tech University, Shanghai, 201210, China 2School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200030, China 3Shanghai United Imaging Intelligence Co., Ltd., Shanghai, 200230, China 4Shanghai Clinical Research and Trial Center, Shanghai, 201210, China |
| Pseudocode | No | The paper describes the methodology using textual explanations and diagrams (e.g., Figure 1, Figure 2, Figure 3) but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code https://github.com/Abster Zhu/MUC |
| Open Datasets | Yes | Human3.6M (Ionescu et al. 2013) is a large-scale multi-view dataset with ground-truth 3D human pose annotation. ... RICH (Huang et al. 2022) is an in-the-wild and indoor multi-view dataset annotated with ground-truth 2D keypoints and 3D body mesh. |
| Dataset Splits | Yes | Human3.6M (Ionescu et al. 2013) is a large-scale multi-view dataset with ground-truth 3D human pose annotation. We follow the standard training/testing split: using subjects S1, S5, S6, S7 and S8 for training, and subjects S9 and S11 for testing. ... RICH (Huang et al. 2022) ... We adopt the intrinsic training/testing split in the dataset. ... For each sample in the training and validation sets, we randomly split it into two samples, each with a camera count equal to 4. |
| Hardware Specification | Yes | All model are trained using single A100 with pytorch. |
| Software Dependencies | No | The paper mentions 'pytorch' as the framework used for training but does not provide a specific version number or other software dependencies with version numbers. |
| Experiment Setup | Yes | Adam optimizer with an initial learning rate of 3 10 5 for 20 epochs. The initialization weight of encoder from SMPLer-X (Cai et al. 2023). |