What type of study is this?

September 10, 2025

HyPoseNet: A Hybrid CNN for 6D Pose Estimation with Point Feature Convolution and Attention Fusion

Key Points

The method achieves an accuracy of 96.9% using the ADD metric on the LineMOD dataset, indicating high performance.
A convolutional block attention module enhances the model by recalibrating feature maps dynamically for better focus.
Integration of segmentation and pose regression enhances target feature extraction and model robustness.
Extensive experiments on benchmark datasets validate the proposed method's superior performance in pose estimation.

Abstract

Abstract The application of RGB-D image data in tasks such as intelligent perception and pose estimation for robots has recently garnered significant attention. A major challenge is effectively utilizing the complementary modalities in RGB-D data sources. A 6D pose estimation method based on the multimodal fusion method, with a hybrid convolutional neural network (CNN) architecture integrating point feature convolution and attention mechanism is proposed in this study. The method integrated a two-stage framework for segmentation and pose regression of RGB-D data, effectively extracting target features and enhancing the model's interpretability and robustness. A convolutional block attention module is introduced to recalibrate the feature maps dynamically, which focuses on information-rich regions and channels, thereby improving the overall performance. Through extensive experiments conducted on benchmark datasets, the proposed method demonstrated remarkable results in target pose estimation: achieving an average accuracy of 96.9% using the ADD metric on the LineMOD dataset, 94.6% using the ADD-S AUC metric on the YCB-Video dataset, and an average ADD-S accuracy of less than 2 cm of 97.7%. These results highlight the superior performance of the proposed approach.

Ask AI

Mark Helpful

Bookmark

Relay