# 6D Pose Estimation with Correlation Fusion

arXiv: https://arxiv.org/abs/1909.12936 · HTML: https://mlsanity.com/paper/1909.12936/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation](https://mlsanity.com/paper/2108.09916/) (2021)
- [DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimation](https://mlsanity.com/paper/2112.08775/) (2021)
- [Attention Models for Point Clouds in Deep Learning: A Survey](https://mlsanity.com/paper/2102.10788/) (2021)
- [End-to-end Reinforcement Learning of Robotic Manipulation with Robust Keypoints Representation](https://mlsanity.com/paper/2202.06027/) (2022)
- [GloCAL: Glocalized Curriculum-Aided Learning of Multiple Tasks with Application to Robotic Grasping](https://mlsanity.com/paper/2204.06835/) (2022)
- [MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation](https://mlsanity.com/paper/2604.20650/) (2026)

## Abstract (arXiv)

6D object pose estimation is widely applied in robotic tasks such as grasping and manipulation. Prior methods using RGB-only images are vulnerable to heavy occlusion and poor illumination, so it is important to complement them with depth information. However, existing methods using RGB-D data cannot adequately exploit consistent and complementary information between RGB and depth modalities. In this paper, we present a novel method to effectively consider the correlation within and across both modalities with attention mechanism to learn discriminative and compact multi-modal features. Then, effective fusion strategies for intra- and inter-correlation modules are explored to ensure efficient information flow between RGB and depth. To our best knowledge, this is the first work to explore effective intra- and inter-modality fusion in 6D pose estimation. The experimental results show that our method can achieve the state-of-the-art performance on LineMOD and YCB-Video dataset. We also demonstrate that the proposed method can benefit a real-world robot grasping task by providing accurate object pose estimation.