Leveraging Multiscale Features and Dynamic Graph Convolution for Robust 6D Pose Estimation
Haodu Zhang, Huafeng Wang, Wanquan Liu, Kexin Guo, Weifeng Lyu, Jun Zhang · IEEE Transactions on Instrumentation and Measurement · 2025
6D pose estimation from RGB-D data remains a challenging task, particularly due to the suboptimal fusion of multi-modal features and the effective utilization of depth information. Most of existing methods often struggle with misalignment between features from different modalities and neglect the importance of multi-scale context. To address these issues, we propose a novel framework, PYN, that leverages multiscale feature fusion and a novel Multi-Hedron Dynamic Graph Convolution Network (MHDGCN). PYN effectively aligns multimodal features across different semantic levels, while MHDGCN efficiently extracts features from irregular depth data, especially in low-quality scenarios. Extensive experiments demonstrate the superiority of our approach over state-of-the-art methods, highlighting its robustness and accuracy in challenging 6D pose estimation tasks. Please check https://github.com/ZEROhands/MSFMHDGCN-Pose for details.