期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
卷 -, 期 -, 页码 7645-7655出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.00756
关键词
-
资金
- National Research Foundation, Singapore under its Strategic Capability Research Centres Funding Initiative
The proposed method integrates top-down and bottom-up approaches to address challenges in multi-person pose estimation, such as inter-person occlusion and scale variations. A two-person pose discriminator is introduced to assess natural interactions, unlike traditional single-person pose discriminators. Additionally, a semi-supervised method is utilized to overcome the scarcity of 3D ground-truth data, showing the effectiveness of the approach in quantitative and qualitative evaluations.
In monocular video 3D multi-person pose estimation, inter-person occlusion and close interactions can cause human detection to be erroneous and human-joints grouping to be unreliable. Existing top-down methods rely on human detection and thus suffer from these problems. Existing bottom-up methods do not use human detection, but they process all persons at once at the same scale, causing them to be sensitive to multiple-persons scale variations. To address these challenges, we propose the integration of top-down and bottom-up approaches to exploit their strengths. Our top-down network estimates human joints from all persons instead of one in an image patch, making it robust to possible erroneous bounding boxes. Our bottom-up network incorporates human-detection based normalized heatmaps, allowing the network to be more robust in handling scale variations. Finally, the estimated 3D poses from the top-down and bottom-up networks are fed into our integration network for final 3D poses. Besides the integration of top-down and bottom-up networks, unlike existing pose discriminators that are designed solely for a single person, and consequently cannot assess natural interperson interactions, we propose a two-person pose discriminator that enforces natural two-person interactions. Lastly, we also apply a semi-supervised method to overcome the 3D ground-truth data scarcity. Quantitative and qualitative evaluations show the effectiveness of the proposed method. Our code is available publicly.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据