Robust 2D Human Pose Estimation with Parallel Graph–Attention Modeling and Entropy-Aware Feature Decoding

TL;DR

This paper introduces PMNet, a new method for 2D human pose estimation that improves accuracy by reducing uncertainty from occlusion and background interference.

Contribution

PMNet combines parallel graph-attention modeling with entropy-aware decoding to enhance robustness in pose estimation.

Findings

PMNet achieves 92.42% PCKh@0.5 on the MPII benchmark and 77.3% AP on COCO.

Ablation studies confirm the effectiveness of components like criss-cross attention and error-compensated decoding.

The method improves signal-to-noise ratios and heatmap concentration for better keypoint localization.

Abstract

Robust 2D human pose estimation remains challenging due to occlusion and background interference, which introduce substantial uncertainty into visual representations. This paper proposes PMNet, a Parallel Modeling Network that integrates explicit graph-based structural modeling and implicit self-attention-based semantic modeling through parallel pathways to jointly capture local dependencies and global contextual relationships among keypoints. From an information-theoretic perspective, occlusion and clutter can be interpreted as sources of increased representational entropy, and PMNet addresses this issue by progressively reducing uncertainty through complementary structural reasoning and attention-based information selection. The framework incorporates a criss-cross attention module to suppress irrelevant features, an adaptive nonlinear fusion strategy to balance complementary information across parallel branches, and an error-compensated decoding method to sharpen heatmap distributions and refine keypoint localization while maintaining efficiency. Extensive experiments on the MPII and COCO benchmarks demonstrate that PMNet achieves state-of-the-art or comparable performance, attaining 92.42% PCKh@0.5 on MPII and 77.3% AP on COCO. Ablation studies and qualitative visualizations further confirm the effectiveness of each component, showing improved signal-to-noise ratios and more concentrated heatmap responses. Overall, PMNet provides a robust and efficient pose estimation framework with strong potential for real-world applications such as surveillance and autonomous systems.

Figures