2025 Object Pose Estimation论文列表

博主： Karl
发布时间：2025 年 10 月 30 日
14 次浏览
暂无评论
15769字数
分类：论文列表

### CVPR 2025

| 序号 | 标题                                                         | 方法分类     | 论文链接                                                     | 代码链接                                                     | 是否可复现 |
| ---- | ------------------------------------------------------------ | ------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ---------- |
| 1    | Any6D: Model-free 6D Pose Estimation of Novel Object         | 任意物体方法 | [https://arxiv.org/abs/2503.18673](https://arxiv.org/abs/2503.18673) | [https://github.com/taeyeopl/Any6D](https://github.com/taeyeopl/Any6D) |            |
| 2    | Co-op: Correspondence-based Novel Object Pose Estimation     | 任意物体方法 | [https://arxiv.org/abs/2503.17731](https://arxiv.org/abs/2503.17731) | 未开源                                                       |            |
| 3    | CRISP: Object Pose and Shape Estimation with Test-Time Adaptation | 实例级方法   | [https://arxiv.org/abs/2412.01052](https://arxiv.org/abs/2412.01052) | [https://github.com/MIT-SPARK/CRISP](https://github.com/MIT-SPARK/CRISP) |            |
| 4    | GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation | 类别级方法   | [https://arxiv.org/abs/2502.04293](https://arxiv.org/abs/2502.04293) | 未开源                                                       |            |
| 5    | GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation | 类别级方法   | [https://arxiv.org/abs/2503.15110](https://arxiv.org/abs/2503.15110) | [https://github.com/ziqin-h/GIVEPose](https://github.com/ziqin-h/GIVEPose) |            |
| 6    | iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting | 任意物体方法 | [https://openaccess.thecvf.com/content/CVPR2025/papers/Cao_iG-6DoF_Model-free_6DoF_Pose_Estimation_for_Unseen_Object_via_Iterative_CVPR_2025_paper.pdf](https://openaccess.thecvf.com/content/CVPR2025/papers/Cao_iG-6DoF_Model-free_6DoF_Pose_Estimation_for_Unseen_Object_via_Iterative_CVPR_2025_paper.pdf) | 未开源                                                       |            |
| 7    | Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images | 类别级方法   | [https://openaccess.thecvf.com/content/CVPR2025/papers/Qiu_Leveraging_Global_Stereo_Consistency_for_Category-Level_Shape_and_6D_Pose_CVPR_2025_paper.pdf](https://openaccess.thecvf.com/content/CVPR2025/papers/Qiu_Leveraging_Global_Stereo_Consistency_for_Category-Level_Shape_and_6D_Pose_CVPR_2025_paper.pdf) | 未开源                                                       |            |
| 8    | ONDA-Pose: Occlusion-Aware Neural Domain Adaptation for Self-Supervised 6D Object Pose Estimation | 实例级方法   | [https://openaccess.thecvf.com/content/CVPR2025/papers/Tan_ONDA-Pose_Occlusion-Aware_Neural_Domain_Adaptation_for_Self-Supervised_6D_Object_Pose_CVPR_2025_paper.pdf](https://openaccess.thecvf.com/content/CVPR2025/papers/Tan_ONDA-Pose_Occlusion-Aware_Neural_Domain_Adaptation_for_Self-Supervised_6D_Object_Pose_CVPR_2025_paper.pdf) | 未开源                                                       |            |
| 9    | One2Any: One-Reference 6D Pose Estimation for Any Object     | 任意物体方法 | [https://arxiv.org/pdf/2505.04109](https://arxiv.org/pdf/2505.04109) | [https://github.com/lmy1001/One2Any](https://github.com/lmy1001/One2Any) |            |
| 10   | Pos3R: 6D Pose Estimation for Unseen Objects Made Easy       | 任意物体方法 | [https://openaccess.thecvf.com/content/CVPR2025/papers/Deng_Pos3R_6D_Pose_Estimation_for_Unseen_Objects_Made_Easy_CVPR_2025_paper.pdf](https://openaccess.thecvf.com/content/CVPR2025/papers/Deng_Pos3R_6D_Pose_Estimation_for_Unseen_Objects_Made_Easy_CVPR_2025_paper.pdf) | 未开源                                                       |            |
| 11   | RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects | 任意物体方法 | [https://arxiv.org/pdf/2505.10841](https://arxiv.org/pdf/2505.10841) | 未开源                                                       |            |
| 12   | Rethinking Correspondence-based Category-Level Object Pose Estimation | 类别级方法   | [https://openaccess.thecvf.com/content/CVPR2025/papers/Ren_Rethinking_Correspondence-based_Category-Level_Object_Pose_Estimation_CVPR_2025_paper.pdf](https://openaccess.thecvf.com/content/CVPR2025/papers/Ren_Rethinking_Correspondence-based_Category-Level_Object_Pose_Estimation_CVPR_2025_paper.pdf) | 空仓库：[https://github.com/RenHuan1999/SpotPose](https://github.com/RenHuan1999/SpotPose) |            |
| 13   | SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow | 实例级方法   | [https://arxiv.org/pdf/2504.09160](https://arxiv.org/pdf/2504.09160) | [https://github.com/W-QY/SCFlow2](https://github.com/W-QY/SCFlow2) |            |
| 14   | Structure-Aware Correspondence Learning for Relative Pose Estimation | 任意物体方法 | [https://arxiv.org/pdf/2503.18671](https://arxiv.org/pdf/2503.18671) | 空仓库：[https://github.com/Cyhhzo02/SAC-Pose-code](https://github.com/Cyhhzo02/SAC-Pose-code) |            |
| 15   | UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References | 实例级方法   | [https://arxiv.org/pdf/2506.07996](https://arxiv.org/pdf/2506.07996) | 未开源                                                       |            |
| 16   | UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image | 任意物体方法 | [https://arxiv.org/pdf/2411.16106](https://arxiv.org/pdf/2411.16106) | [https://github.com/shanice-l/UNOPose](https://github.com/shanice-l/UNOPose) |            |

### ICCV 2025

### NIPS 2025

| 序号 | 标题                                                         | 方法分类     | 论文链接                                                     | 代码链接 | 是否可复现 |
| ---- | ------------------------------------------------------------ | ------------ | ------------------------------------------------------------ | -------- | ---------- |
| 1    | RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching | 类别级方法   | 未开源                                                       |          |            |
| 2    | SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference | 任意物体方法 | [https://arxiv.org/pdf/2509.21927](https://arxiv.org/pdf/2509.21927) |          |            |

### AAAI 2025

| 序号 | 标题                                                         | 方法分类   | 论文链接                                                     | 代码链接 | 是否可复现 |
| ---- | ------------------------------------------------------------ | ---------- | ------------------------------------------------------------ | -------- | ---------- |
| 1    | KeyPose: Category-Level 6D Object Pose Estimation with Self-Adaptive Keypoints | 类别级方法 | [https://ojs.aaai.org/index.php/AAAI/article/view/33046/35201](https://ojs.aaai.org/index.php/AAAI/article/view/33046/35201) | 未开源   |            |
| 2    | Universal Features Guided Zero-Shot Category-Level Object Pose Estimation | 类别级方法 | [https://arxiv.org/pdf/2501.02831](https://arxiv.org/pdf/2501.02831) | 未开源   |            |

### MM 2025

| 序号 | 标题                                                         | 方法分类     | 论文链接                                                     | 代码链接 | 是否可复现 |
| ---- | ------------------------------------------------------------ | ------------ | ------------------------------------------------------------ | -------- | ---------- |
| 1    | CLIP-6D: Empowering CLIP as a Zero-Shot 6D Pose Estimator Through Generalizable Object-Specific Representations | 任意物体方法 | [https://dl.acm.org/doi/pdf/10.1145/3746027.3754497](https://dl.acm.org/doi/pdf/10.1145/3746027.3754497) | 未开源   |            |

### ICRA 2025

| 序号 | 标题                                                         | 方法分类   | 论文链接                                                     | 代码链接                                                     | 是否可复现 |
| ---- | ------------------------------------------------------------ | ---------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ---------- |
| 1    | A Unified End-to-End Network for Category-Level and Instance-Level Object Pose Estimation from RGB Images | 类别级方法 | [https://ieeexplore.ieee.org/document/11128247](https://ieeexplore.ieee.org/document/11128247) | 未开源                                                       |            |
| 2    | MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model | 类别级方法 | [https://ieeexplore.ieee.org/document/11127837](https://ieeexplore.ieee.org/document/11127837) | [https://github.com/CNJianLiu/MonoDiff9D](https://github.com/CNJianLiu/MonoDiff9D) |            |
| 3    | Occlusion-Aware 6D Pose Estimation with Depth-Guided Graph Encoding and Cross-Semantic Fusion for Robotic Grasping | 实例级方法 | [https://ieeexplore.ieee.org/document/11128248](https://ieeexplore.ieee.org/document/11128248) | 未开源                                                       |            |

### 方法分类

#### 实例级方法

1. CVPR 2025：
   1. CRISP: Object Pose and Shape Estimation with Test-Time Adaptation
   2. ONDA-Pose: Occlusion-Aware Neural Domain Adaptation for Self-Supervised 6D Object Pose Estimation
   3. SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow
   4. UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References
2. ICCV 2025：
   1. 6DOPE-GS: Online 6D Object Pose Estimation using Gaussian
   2. Deterministic Object Pose Confidence Region Estimation
   3. Environment-Agnostic Pose: Generating Environment-independent Object Representations for 6D Pose Estimation
   4. HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation
3. NIPS 2025：
   1. 无
4. AAAI 2025：
   1. 无
5. MM 2025：
   1. 无
6. ICRA 2025：
   1. Occlusion-aware 6D Pose Estimation with Depth-guided Graph Encoding and Cross-semantic Fusion for Robotic Grasping

#### 类别级方法

1. CVPR 2025：
   1. GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation
   2. GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation
   3. Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images
   4. Rethinking Correspondence-based Category-Level Object Pose Estimation
2. ICCV 2025：
   1. CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation
   2. Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation
   3. Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes
3. NIPS 2025：
   1. RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching
4. AAAI 2025：
   1. KeyPose: Category-Level 6D Object Pose Estimation with Self-Adaptive Keypoints
   2. Universal Features Guided Zero-Shot Category-Level Object Pose Estimation
5. MM 2025：
   1. 无
6. ICRA 2025：
   1. A Unified End-to-end Network for Category-level and Instance-level Object Pose Estimation from RGB Images
   2. MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model

#### 任意物体方法

1. CVPR 2025：
   1. Any6D: Model-free 6D Pose Estimation of Novel Object
   2. Co-op: Correspondence-based Novel Object Pose Estimation
   3. iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting
   4. One2Any: One-Reference 6D Pose Estimation for Any Object
   5. Pos3R: 6D Pose Estimation for Unseen Objects Made Easy
   6. RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects
   7. Structure-Aware Correspondence Learning for Relative Pose Estimation
   8. UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
2. ICCV 2025：
   1. BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation
   2. MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation
   3. RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation
3. NIPS 2025：
   1. SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference
4. AAAI 2025：
   1. 无
5. MM 2025：
   1. CLIP-6D: Empowering CLIP as a Zero-Shot 6D Pose Estimator Through Generalizable Object-Specific Representations
6. ICRA 2025：
   1. 无

最后修改：2025 年 11 月 04 日

如果觉得我的文章对你有用，请随意赞赏。

发表评论取消回复
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款。

评论 *

私密评论

名称 *

🎲

邮箱 *

地址

2025 Object Pose Estimation论文列表

Karl • 2025 年 10 月 30 日

### CVPR 2025

### ICCV 2025

### NIPS 2025

| 序号 | 标题                                                         | 方法分类     | 论文链接                                                     | 代码链接 | 是否可复现 |
| ---- | ------------------------------------------------------------ | ------------ | ------------------------------------------------------------ | -------- | ---------- |
| 1    | RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching | 类别级方法   | 未开源                                                       |          |            |
| 2    | SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference | 任意物体方法 | [https://arxiv.org/pdf/2509.21927](https://arxiv.org/pdf/2509.21927) |          |            |

### AAAI 2025

| 序号 | 标题                                                         | 方法分类   | 论文链接                                                     | 代码链接 | 是否可复现 |
| ---- | ------------------------------------------------------------ | ---------- | ------------------------------------------------------------ | -------- | ---------- |
| 1    | KeyPose: Category-Level 6D Object Pose Estimation with Self-Adaptive Keypoints | 类别级方法 | [https://ojs.aaai.org/index.php/AAAI/article/view/33046/35201](https://ojs.aaai.org/index.php/AAAI/article/view/33046/35201) | 未开源   |            |
| 2    | Universal Features Guided Zero-Shot Category-Level Object Pose Estimation | 类别级方法 | [https://arxiv.org/pdf/2501.02831](https://arxiv.org/pdf/2501.02831) | 未开源   |            |

### MM 2025

| 序号 | 标题                                                         | 方法分类     | 论文链接                                                     | 代码链接 | 是否可复现 |
| ---- | ------------------------------------------------------------ | ------------ | ------------------------------------------------------------ | -------- | ---------- |
| 1    | CLIP-6D: Empowering CLIP as a Zero-Shot 6D Pose Estimator Through Generalizable Object-Specific Representations | 任意物体方法 | [https://dl.acm.org/doi/pdf/10.1145/3746027.3754497](https://dl.acm.org/doi/pdf/10.1145/3746027.3754497) | 未开源   |            |

### ICRA 2025

| 序号 | 标题                                                         | 方法分类   | 论文链接                                                     | 代码链接                                                     | 是否可复现 |
| ---- | ------------------------------------------------------------ | ---------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ---------- |
| 1    | A Unified End-to-End Network for Category-Level and Instance-Level Object Pose Estimation from RGB Images | 类别级方法 | [https://ieeexplore.ieee.org/document/11128247](https://ieeexplore.ieee.org/document/11128247) | 未开源                                                       |            |
| 2    | MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model | 类别级方法 | [https://ieeexplore.ieee.org/document/11127837](https://ieeexplore.ieee.org/document/11127837) | [https://github.com/CNJianLiu/MonoDiff9D](https://github.com/CNJianLiu/MonoDiff9D) |            |
| 3    | Occlusion-Aware 6D Pose Estimation with Depth-Guided Graph Encoding and Cross-Semantic Fusion for Robotic Grasping | 实例级方法 | [https://ieeexplore.ieee.org/document/11128248](https://ieeexplore.ieee.org/document/11128248) | 未开源                                                       |            |

### 方法分类

#### 实例级方法

#### 类别级方法

#### 任意物体方法

2025 Object Pose Estimation论文列表

发表评论取消回复
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款。

欢迎使用 Typecho

vim配置文件

tmux配置文件

2025 Object Pose Estimation论文列表

tmux配置文件

欢迎使用 Typecho

2025 Object Pose Estimation论文列表

vim配置文件

2025 Object Pose Estimation论文列表

发表评论 取消回复 使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款。

2025 Object Pose Estimation论文列表

发表评论取消回复
使用cookie技术保留您的个人信息以便您下次快速评论，继续评论表示您已同意该条款。