CIGPose：基于因果干预图的全身姿态估计神经网络
CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation
AI总结：
本文提出CIGPose框架，通过因果干预模块消除视觉上下文的干扰，提升全身姿态估计的鲁棒性与准确性，实验表明其在COCO-WholeBody上达到新状态-of-the-art。
摘要：
最先进的全身姿态估计器往往缺乏鲁棒性，在挑战性场景中产生不符合人体解剖学的预测。我们提出这种失败源于从视觉上下文中学习到的虚假相关性，我们通过结构性因果模型（SCM）正式化这一问题。SCM将视觉上下文识别为一个混杂因素，创建了非因果的后门路径，破坏了模型的推理。我们引入因果干预图姿态（CIGPose）框架来解决这一问题，通过近似视觉证据与姿态之间的真正因果效应。CIGPose的核心是一个新的因果干预模块：它首先通过预测不确定性识别受混淆的关键点表示，然后用学习到的、与上下文无关的规范嵌入替换它们。这些去混淆的嵌入通过层次图神经网络进行处理，该网络在局部和全局语义层面推理人类骨骼，以强制符合解剖学合理性。广泛的实验表明，CIGPose在COCO-WholeBody上实现了新的state-of-the-art。值得注意的是，我们的CIGPose-x模型达到67.0%的AP，超过了依赖额外训练数据的先前方法。在加入UBody数据集后，CIGPose-x进一步提升到67.5%的AP，展示了优越的鲁棒性和数据效率。代码和模型在https://github.com/53mins/CIGPose上公开。
英文摘要：
State-of-the-art whole-body pose estimators often lack robustness, producing anatomically implausible predictions in challenging scenes. We posit this failure stems from spurious correlations learned from visual context, a problem we formalize using a Structural Causal Model (SCM). The SCM identifies visual context as a confounder that creates a non-causal backdoor path, corrupting the model's reasoning. We introduce the Causal Intervention Graph Pose (CIGPose) framework to address this by approximating the true causal effect between visual evidence and pose. The core of CIGPose is a novel Causal Intervention Module: it first identifies confounded keypoint representations via predictive uncertainty and then replaces them with learned, context-invariant canonical embeddings. These deconfounded embeddings are processed by a hierarchical graph neural network that reasons over the human skeleton at both local and global semantic levels to enforce anatomical plausibility. Extensive experiments show CIGPose achieves a new state-of-the-art on COCO-WholeBody. Notably, our CIGPose-x model achieves 67.0\% AP, surpassing prior methods that rely on extra training data. With the additional UBody dataset, CIGPose-x is further boosted to 67.5\% AP, demonstrating superior robustness and data efficiency. The codes and models are publicly available at https://github.com/53mins/CIGPose.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
