用深度图提升多人姿态估计速度与可靠性
SimpleDepthPose: Fast and Reliable Human Pose Estimation with RGBD-Images
- 融合深度信息实现多视角多人姿态估计
- 在未见数据集上表现稳定，推理速度快
- 支持多种关键点，适合实际部署场景
在计算机视觉快速发展的背景下，从多视角准确估计多人姿态仍是重大挑战，尤其对可靠性要求较高时。本文提出一种新算法，通过引入深度信息，在多视角、多人姿态估计任务中表现优异。大量实验表明，该算法不仅在未见过的数据集上具有良好的泛化能力，且运行速度快，同时可适配不同关键点定义。为促进后续研究，所有代码与资源均已公开。
原文摘要 · Abstract (English)
In the rapidly advancing domain of computer vision, accurately estimating the poses of multiple individuals from various viewpoints remains a significant challenge, especially when reliability is a key requirement. This paper introduces a novel algorithm that excels in multi-view, multi-person pose estimation by incorporating depth information. An extensive evaluation demonstrates that the proposed algorithm not only generalizes well to unseen datasets, and shows a fast runtime performance, but also is adaptable to different keypoints. To support further research, all of the work is publicly accessible.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。