通过盒子、掩码和姿态的循环互校，提升多人重叠场景下的检测与姿态估计效果。
Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
- 设计盒子-掩码-姿态闭环，三者相互条件优化，增强多人体场景鲁棒性。
- 在OCHuman上三项任务均达顶尖性能，重叠场景检测率比基线高39%。
- 模型轻量高效，适合部署，特别适合复杂遮挡多人场景应用。
人体姿态估计方法在孤立人物上表现良好，但在多人近距离场景中表现不佳。以往工作通过边界框或关键点来引导姿态估计，却忽略了实例掩码。本文提出一种迭代互校框架，联合优化边界框、实例掩码和姿态。BBox-Mask-Pose（BMP）方法采用三个专用模型，在闭环中相互提升。其中新提出的MaskPose是当前自顶向下方法中在OCHuman数据集上表现最佳。BMP在OCHuman上三项任务均达到最先进水平，并在COCO姿态估计上也取得领先。尤其在大重叠场景中，检测性能相比基线提升39%。模型体积小、运行快，是大型人体基础模型的高效替代方案。代码与模型已公开于https://MiraPurkrabek.github.io/BBox-Mask-Pose。
原文摘要 · Abstract (English)
Human pose estimation methods work well on isolated people but struggle with multiple-bodies-in-proximity scenarios. Previous work has addressed this problem by conditioning pose estimation by detected bounding boxes or keypoints, but overlooked instance masks. We propose to iteratively enforce mutual consistency of bounding boxes, instance masks, and poses. The introduced BBox-Mask-Pose (BMP) method uses three specialized models that improve each other's output in a closed loop. All models are adapted for mutual conditioning, which improves robustness in multi-body scenes. MaskPose, a new mask-conditioned pose estimation model, is the best among top-down approaches on OCHuman. BBox-Mask-Pose pushes SOTA on OCHuman dataset in all three tasks - detection, instance segmentation, and pose estimation. It also achieves SOTA performance on COCO pose estimation. The method is especially good in scenes with large instances overlap, where it improves detection by 39% over the baseline detector. With small specialized models and faster runtime, BMP is an effective alternative to large human-centered foundational models. Code and models are available on https://MiraPurkrabek.github.io/BBox-Mask-Pose.
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。