DualPose: Dual-Block Transformer Decoder with Contrastive Denoising for Multi-Person Pose Estimation
Multi-person pose estimation is the task of detecting and regressing the keypoint coordinates of multiple people in a single image. Significant progress has been achieved in recent years, especially with the introduction of transformer-based end-to-end methods. In this paper, we present DualPose, a...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/10/2997 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850256146769641472 |
|---|---|
| author | Matteo Fincato Roberto Vezzani |
| author_facet | Matteo Fincato Roberto Vezzani |
| author_sort | Matteo Fincato |
| collection | DOAJ |
| description | Multi-person pose estimation is the task of detecting and regressing the keypoint coordinates of multiple people in a single image. Significant progress has been achieved in recent years, especially with the introduction of transformer-based end-to-end methods. In this paper, we present DualPose, a novel framework that enhances multi-person pose estimation by leveraging a dual-block transformer decoding architecture. Class prediction and keypoint estimation are split into parallel blocks so each sub-task can be separately improved and the risk of interference is reduced. This architecture improves the precision of keypoint localization and the model’s capacity to accurately classify individuals. To improve model performance, the Keypoint-Block uses parallel processing of self-attentions, providing a novel strategy that improves keypoint localization accuracy and precision. Additionally, DualPose incorporates a contrastive denoising (CDN) mechanism, leveraging positive and negative samples to stabilize training and improve robustness. Thanks to CDN, a variety of training samples are created by introducing controlled noise into the ground truth, improving the model’s ability to discern between valid and incorrect keypoints. DualPose achieves state-of-the-art results outperforming recent end-to-end methods, as shown by extensive experiments on the MS COCO and CrowdPose datasets. The code and pretrained models are publicly available. |
| format | Article |
| id | doaj-art-b85c7af2d22f4fe3ac49daeab403932f |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-b85c7af2d22f4fe3ac49daeab403932f2025-08-20T01:56:42ZengMDPI AGSensors1424-82202025-05-012510299710.3390/s25102997DualPose: Dual-Block Transformer Decoder with Contrastive Denoising for Multi-Person Pose EstimationMatteo Fincato0Roberto Vezzani1Department of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, Via P. Vivarelli 10, 41125 Modena, ItalyDepartment of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, Via P. Vivarelli 10, 41125 Modena, ItalyMulti-person pose estimation is the task of detecting and regressing the keypoint coordinates of multiple people in a single image. Significant progress has been achieved in recent years, especially with the introduction of transformer-based end-to-end methods. In this paper, we present DualPose, a novel framework that enhances multi-person pose estimation by leveraging a dual-block transformer decoding architecture. Class prediction and keypoint estimation are split into parallel blocks so each sub-task can be separately improved and the risk of interference is reduced. This architecture improves the precision of keypoint localization and the model’s capacity to accurately classify individuals. To improve model performance, the Keypoint-Block uses parallel processing of self-attentions, providing a novel strategy that improves keypoint localization accuracy and precision. Additionally, DualPose incorporates a contrastive denoising (CDN) mechanism, leveraging positive and negative samples to stabilize training and improve robustness. Thanks to CDN, a variety of training samples are created by introducing controlled noise into the ground truth, improving the model’s ability to discern between valid and incorrect keypoints. DualPose achieves state-of-the-art results outperforming recent end-to-end methods, as shown by extensive experiments on the MS COCO and CrowdPose datasets. The code and pretrained models are publicly available.https://www.mdpi.com/1424-8220/25/10/2997contrastive denoisingDualPosehuman pose estimationmulti-person pose estimationtransformer-based models |
| spellingShingle | Matteo Fincato Roberto Vezzani DualPose: Dual-Block Transformer Decoder with Contrastive Denoising for Multi-Person Pose Estimation Sensors contrastive denoising DualPose human pose estimation multi-person pose estimation transformer-based models |
| title | DualPose: Dual-Block Transformer Decoder with Contrastive Denoising for Multi-Person Pose Estimation |
| title_full | DualPose: Dual-Block Transformer Decoder with Contrastive Denoising for Multi-Person Pose Estimation |
| title_fullStr | DualPose: Dual-Block Transformer Decoder with Contrastive Denoising for Multi-Person Pose Estimation |
| title_full_unstemmed | DualPose: Dual-Block Transformer Decoder with Contrastive Denoising for Multi-Person Pose Estimation |
| title_short | DualPose: Dual-Block Transformer Decoder with Contrastive Denoising for Multi-Person Pose Estimation |
| title_sort | dualpose dual block transformer decoder with contrastive denoising for multi person pose estimation |
| topic | contrastive denoising DualPose human pose estimation multi-person pose estimation transformer-based models |
| url | https://www.mdpi.com/1424-8220/25/10/2997 |
| work_keys_str_mv | AT matteofincato dualposedualblocktransformerdecoderwithcontrastivedenoisingformultipersonposeestimation AT robertovezzani dualposedualblocktransformerdecoderwithcontrastivedenoisingformultipersonposeestimation |