CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimation

TL;DR

CIGPose introduces a causal intervention framework for whole-body pose estimation that improves robustness and anatomical plausibility by addressing confounding visual context through a novel graph neural network approach.

Contribution

This work presents a new causal intervention method with a graph neural network to enhance pose estimation accuracy and robustness, outperforming existing models on multiple datasets.

Findings

Achieves state-of-the-art results on COCO-WholeBody dataset.

Surpasses prior methods with 67.0% AP without extra data.

Demonstrates improved robustness and data efficiency.

Abstract

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.