Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2401.16284 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929227180277760 |
|---|---|
| author | Park, Jaewoo Kim, Jaeguk Cho, Nam Ik |
| author_facet | Park, Jaewoo Kim, Jaeguk Cho, Nam Ik |
| contents | Accurately estimating the pose of an object is a crucial task in computer vision and robotics. There are two main deep learning approaches for this: geometric representation regression and iterative refinement. However, these methods have some limitations that reduce their effectiveness. In this paper, we analyze these limitations and propose new strategies to overcome them. To tackle the issue of blurry geometric representation, we use positional encoding with high-frequency components for the object's 3D coordinates. To address the local minimum problem in refinement methods, we introduce a normalized image plane-based multi-reference refinement strategy that's independent of intrinsic matrix constraints. Lastly, we utilize adaptive instance normalization and a simple occlusion augmentation method to help our model concentrate on the target object. Our experiments on Linemod, Linemod-Occlusion, and YCB-Video datasets demonstrate that our approach outperforms existing methods. We will soon release the code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_16284 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimation Park, Jaewoo Kim, Jaeguk Cho, Nam Ik Computer Vision and Pattern Recognition Accurately estimating the pose of an object is a crucial task in computer vision and robotics. There are two main deep learning approaches for this: geometric representation regression and iterative refinement. However, these methods have some limitations that reduce their effectiveness. In this paper, we analyze these limitations and propose new strategies to overcome them. To tackle the issue of blurry geometric representation, we use positional encoding with high-frequency components for the object's 3D coordinates. To address the local minimum problem in refinement methods, we introduce a normalized image plane-based multi-reference refinement strategy that's independent of intrinsic matrix constraints. Lastly, we utilize adaptive instance normalization and a simple occlusion augmentation method to help our model concentrate on the target object. Our experiments on Linemod, Linemod-Occlusion, and YCB-Video datasets demonstrate that our approach outperforms existing methods. We will soon release the code. |
| title | Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.16284 |