提出概率化人体姿态估计新方法，更好处理图像外关键点。
ProbPose: A Probabilistic Approach to 2D Human Pose Estimation
- 用概率分布建模关键点位置与可见性，支持图像内外检测。
- 在COCO等数据集上，图像外关键点定位准确率显著提升。
- 新增数据集和评估指标，适合关注鲁棒性与完整姿态分析的研究者。
当前人体姿态估计方法已取得显著进展，但主流模型忽略图像外关键点，且使用未经校准的热图表示关键点位置。为此，我们提出ProbPose，对每个关键点预测：激活窗口内各位置的关键点存在概率、在窗口外的概率，以及其可见性。为解决图像外关键点缺乏评估协议的问题，我们引入CropCOCO数据集与扩展版OKS（Ex-OKS）指标，将OKS扩展至图像外点。在COCO、CropCOCO和OCHuman数据集上的实验表明，ProbPose在图像外关键点定位上表现显著提升，同时通过数据增强提升了图像内定位性能。此外，模型在边界区域更鲁棒，且支持更灵活的关键点评估。代码与模型已在https://mirapurkrabek.github.io/ProbPose/公开用于研究。
原文摘要 · Abstract (English)
Current Human Pose Estimation methods have achieved significant improvements. However, state-of-the-art models ignore out-of-image keypoints and use uncalibrated heatmaps as keypoint location representations. To address these limitations, we propose ProbPose, which predicts for each keypoint: a calibrated probability of keypoint presence at each location in the activation window, the probability of being outside of it, and its predicted visibility. To address the lack of evaluation protocols for out-of-image keypoints, we introduce the CropCOCO dataset and the Extended OKS (Ex-OKS) metric, which extends OKS to out-of-image points. Tested on COCO, CropCOCO, and OCHuman, ProbPose shows significant gains in out-of-image keypoint localization while also improving in-image localization through data augmentation. Additionally, the model improves robustness along the edges of the bounding box and offers better flexibility in keypoint evaluation. The code and models are available on https://mirapurkrabek.github.io/ProbPose/ for research purposes.
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。