CIGPose：面向全身姿态估计的因果干预图神经网络
CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation
把视觉上下文当作混淆因子、用因果干预模块替换被混淆的关键点表征，这一去混淆思路可直接迁移到其他易受上下文虚假关联影响的关键点/密集预测任务（如手部姿态、动物姿态、遮挡场景下的检测）。
原文依据 it first identifies confounded keypoint representations via predictive uncertainty and then replaces them with learned, context-invariant canonical embeddings
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论最优的全身姿态估计器往往缺乏鲁棒性，在具有挑战性的场景中会产生解剖学上不合理的预测。我们认为这一失败源于从视觉上下文中学习到的虚假关联，并用结构因果模型（SCM）对此加以形式化。该 SCM 将视觉上下文识别为混淆因子，它制造了一条非因果的后门路径，从而破坏模型的推理。我们提出因果干预图姿态（CIGPose）框架，通过近似视觉证据与姿态之间的真实因果效应来解决该问题。CIGPose 的核心是一个新颖的因果干预模块：它首先通过预测不确定性识别出被混淆的关键点表征，然后用学习到的、上下文不变的规范嵌入替换它们。这些去混淆后的嵌入由分层图神经网络处理，该网络在局部与全局语义两个层面上对人体骨架进行推理，以强制解剖学合理性。大量实验表明，CIGPose 在 COCO-WholeBody 上取得了新的最优性能。值得注意的是，我们的 CIGPose-x 模型达到 67.0% AP，超过了依赖额外训练数据的先前方法。在额外使用 UBody 数据集后，CIGPose-x 进一步提升至 67.5% AP，展现出更优的鲁棒性与数据效率。
英文原文摘要 1306 字符
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.