LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915614269898752 |
|---|---|
| author | Guo, Biao Zhou, Cong Guo, Fangmin Luo, Xiaonan Luo, Guibo Zhang, Feng |
| author_facet | Guo, Biao Zhou, Cong Guo, Fangmin Luo, Xiaonan Luo, Guibo Zhang, Feng |
| contents | Most of the current top-down multi-person pose estimation lightweight methods are based on multi-branch parallel pure CNN network architecture, which often struggle to capture the global context required for detecting semantically complex keypoints and are hindered by high latency due to their intricate and redundant structures. In this article, an approximate single-branch lightweight global modeling network (LGM-Pose) is proposed to address these challenges. In the network, a lightweight MobileViM Block is designed with a proposed Lightweight Attentional Representation Module (LARM), which integrates information within and between patches using the Non-Parametric Transformation Operation(NPT-Op) to extract global information. Additionally, a novel Shuffle-Integrated Fusion Module (SFusion) is introduced to effectively integrate multi-scale information, mitigating performance degradation often observed in single-branch structures. Experimental evaluations on the COCO and MPII datasets demonstrate that our approach not only reduces the number of parameters compared to existing mainstream lightweight methods but also achieves superior performance and faster processing speeds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_04561 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation Guo, Biao Zhou, Cong Guo, Fangmin Luo, Xiaonan Luo, Guibo Zhang, Feng Computer Vision and Pattern Recognition Most of the current top-down multi-person pose estimation lightweight methods are based on multi-branch parallel pure CNN network architecture, which often struggle to capture the global context required for detecting semantically complex keypoints and are hindered by high latency due to their intricate and redundant structures. In this article, an approximate single-branch lightweight global modeling network (LGM-Pose) is proposed to address these challenges. In the network, a lightweight MobileViM Block is designed with a proposed Lightweight Attentional Representation Module (LARM), which integrates information within and between patches using the Non-Parametric Transformation Operation(NPT-Op) to extract global information. Additionally, a novel Shuffle-Integrated Fusion Module (SFusion) is introduced to effectively integrate multi-scale information, mitigating performance degradation often observed in single-branch structures. Experimental evaluations on the COCO and MPII datasets demonstrate that our approach not only reduces the number of parameters compared to existing mainstream lightweight methods but also achieves superior performance and faster processing speeds. |
| title | LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.04561 |