| Autor: |
Xiangjun Zhang, Yinglin Zheng, Wenjin Deng, Qifeng Dai, Yuxin Lin, Wangzheng Shi, Ming Zeng |
| Jazyk: |
angličtina |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
Graphical Models, Vol 130, Iss , Pp 101207- (2023) |
| Druh dokumentu: |
article |
| ISSN: |
1524-0703 |
| DOI: |
10.1016/j.gmod.2023.101207 |
| Popis: |
Reconstructing 3D human pose and body shape from monocular images or videos is a fundamental task for comprehending human dynamics. Frame-based methods can be broadly categorized into two fashions: those regressing parametric model parameters (e.g., SMPL) and those exploring alternative representations (e.g., volumetric shapes, 3D coordinates). Non-parametric representations have demonstrated superior performance due to their enhanced flexibility. However, when applied to video data, these non-parametric frame-based methods tend to generate inconsistent and unsmooth results. To this end, we present a novel approach that directly regresses the 3D coordinates of the mesh vertices and body joints with a spatial–temporal Transformer. In our method, we introduce a SpatioTemporal Learning Block (STLB) with Spatial Learning Module (SLM) and Temporal Learning Module (TLM), which leverages spatial and temporal information to model interactions at a finer granularity, specifically at the body token level. Our method outperforms previous state-of-the-art approaches on Human3.6M and 3DPW benchmark datasets. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
Full Text from ScienceDirect