【论文列表】2025年Object Pose Estimation顶会论文列表

博主： karltan0328
发布时间：2026 年 03 月 05 日
3 次浏览
暂无评论
13174字数
分类：论文列表

### CVPR

1. Any6D: Model-free 6D Pose Estimation of Novel Object
   - 任意物体方法
   - 论文PDF：[https://arxiv.org/pdf/2503.18673](https://arxiv.org/pdf/2503.18673)
   - 代码：[https://github.com/taeyeopl/Any6D](https://github.com/taeyeopl/Any6D)
   - 是否可复现：
2. Co-op: Correspondence-based Novel Object Pose Estimation
   - 任意物体方法
   - 论文PDF：[https://arxiv.org/pdf/2503.17731](https://arxiv.org/pdf/2503.17731)
   - 代码未开源
   - 是否可复现：
3. CRISP: Object Pose and Shape Estimation with Test-Time Adaptation
   - 任意物体方法（不确定）
   - 论文PDF：[https://arxiv.org/pdf/2412.01052](https://arxiv.org/pdf/2412.01052)
   - 代码未开源
   - 是否可复现：
4. GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimation
   - 类别级方法
   - 论文PDF：[https://arxiv.org/pdf/2502.04293](https://arxiv.org/pdf/2502.04293)
   - 代码未开源
   - 是否可复现：
5. GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation
   - 类别级方法
   - 论文PDF：[https://arxiv.org/pdf/2503.15110](https://arxiv.org/pdf/2503.15110)
   - 代码：[https://github.com/ziqin-h/GIVEPose](https://github.com/ziqin-h/GIVEPose)
   - 是否可复现：
6. iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting
   - 任意物体方法
   - 论文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](https://openaccess.thecvf.com/content/CVPR2025/papers/Cao_iG-6DoF_Model-free_6DoF_Pose_Estimation_for_Unseen_Object_via_Iterative_CVPR_2025_paper.pdf)
   - 代码未开源
   - 是否可复现：
7. Leveraging Global Stereo Consistency for Category-Level Shape and 6D Pose Estimation from Stereo Images
   - 类别级方法
   - 论文PDF：[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)
   - 代码未开源
   - 是否可复现：
8. ONDA-Pose: Occlusion-Aware Neural Domain Adaptation for Self-Supervised 6D Object Pose Estimation
   - 实例级方法
   - 论文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](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)
   - 代码未开源
   - 是否可复现：
9. One2Any: One-Reference 6D Pose Estimation for Any Object
   - 任意物体方法
   - 论文PDF：[https://arxiv.org/pdf/2505.04109](https://arxiv.org/pdf/2505.04109)
   - 代码：[https://github.com/lmy1001/One2Any](https://github.com/lmy1001/One2Any)
   - 是否可复现：
10. Pos3R: 6D Pose Estimation for Unseen Objects Made Easy
    - 任意物体方法
    - 论文PDF：[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)
    - 代码未开源
    - 是否可复现：
11. RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects
    - 任意物体方法
    - 论文PDF：[https://arxiv.org/pdf/2505.10841](https://arxiv.org/pdf/2505.10841)
    - 代码未开源
    - 是否可复现：
12. Rethinking Correspondence-based Category-Level Object Pose Estimation
    - 类别级方法
    - 论文PDF：[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)
    - 代码：[https://github.com/RenHuan1999/SpotPose](https://github.com/RenHuan1999/SpotPose)（空仓库）
    - 是否可复现：
13. SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow
    - 位姿优化方法
    - 论文PDF：[https://arxiv.org/pdf/2504.09160](https://arxiv.org/pdf/2504.09160)
    - 代码：[https://github.com/W-QY/SCFlow2](https://github.com/W-QY/SCFlow2)
    - 是否可复现：
14. Structure-Aware Correspondence Learning for Relative Pose Estimation
    - 任意物体方法
    - 论文PDF：[https://openaccess.thecvf.com/content/CVPR2025/papers/Chen_Structure-Aware_Correspondence_Learning_for_Relative_Pose_Estimation_CVPR_2025_paper.pdf](https://openaccess.thecvf.com/content/CVPR2025/papers/Chen_Structure-Aware_Correspondence_Learning_for_Relative_Pose_Estimation_CVPR_2025_paper.pdf)
    - 代码未开源
    - 是否可复现：
15. UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References
    - 实例级方法
    - 论文PDF：[https://arxiv.org/pdf/2506.07996](https://arxiv.org/pdf/2506.07996)
    - 代码：[https://github.com/minfenli/UA-Pose](https://github.com/minfenli/UA-Pose)（空仓库）
    - 是否可复现：
16. UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
    - 任意物体方法
    - 论文PDF：[https://arxiv.org/pdf/2411.16106](https://arxiv.org/pdf/2411.16106)
    - 代码：[https://github.com/shanice-l/UNOPose](https://github.com/shanice-l/UNOPose)
    - 是否可复现：

### ICCV

1. 6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting
   - 实例级方法
   - 论文PDF：[https://arxiv.org/pdf/2412.01543](https://arxiv.org/pdf/2412.01543)
   - 代码未开源
   - 是否可复现：
2. BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation
   - 任意物体方法
   - 论文PDF：[https://arxiv.org/pdf/2504.07955](https://arxiv.org/pdf/2504.07955)
   - 代码：[https://github.com/zju3dv/BoxDreamer](https://github.com/zju3dv/BoxDreamer)
   - 是否可复现：
3. CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation
   - 类别级方法
   - 论文PDF：[https://arxiv.org/pdf/2502.01312](https://arxiv.org/pdf/2502.01312)
   - 代码：[https://github.com/chrislin0621/CleanPose](https://github.com/chrislin0621/CleanPose)
   - 是否可复现：是，但复现性能低于论文性能2%左右
4. Deterministic Object Pose Confidence Region Estimation
   - 实例级方法（不确定）
   - 论文PDF：[https://arxiv.org/pdf/2506.22720](https://arxiv.org/pdf/2506.22720)
   - 代码未开源
   - 是否可复现：
5. Environment-Agnostic Pose: Generating Environment-independent Object Representations for 6D Pose Estimation
   - 实例级方法
   - 论文PDF：[https://openaccess.thecvf.com/content/ICCV2025/papers/Zhang_Environment-Agnostic_Pose_Generating_Environment-independent_Object_Representations_for_6D_Pose_Estimation_ICCV_2025_paper.pdf](https://openaccess.thecvf.com/content/ICCV2025/papers/Zhang_Environment-Agnostic_Pose_Generating_Environment-independent_Object_Representations_for_6D_Pose_Estimation_ICCV_2025_paper.pdf)
   - 代码：[https://github.com/acmff22/EA6D](https://github.com/acmff22/EA6D)
   - 是否可复现：
6. HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation
   - 实例级方法
   - 论文PDF：[https://arxiv.org/pdf/2510.10177](https://arxiv.org/pdf/2510.10177)
   - 代码：[https://github.com/WangYuLin-SEU/HCCEPose](https://github.com/WangYuLin-SEU/HCCEPose)
   - 是否可复现：
7. Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation
   - 类别级方法
   - 论文PDF：[https://arxiv.org/pdf/2510.04125](https://arxiv.org/pdf/2510.04125)
   - 代码未开源
   - 是否可复现：
8. MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation
   - 任意物体方法
   - 论文PDF：[https://arxiv.org/pdf/2601.06883](https://arxiv.org/pdf/2601.06883)
   - 代码未开源
   - 是否可复现：
9. RayPose: Ray Bundling Diffusion for Template Views in Unseen 6D Object Pose Estimation
   - 任意物体方法
   - 论文PDF：[https://arxiv.org/pdf/2510.18521](https://arxiv.org/pdf/2510.18521)
   - 代码未开源
   - 是否可复现：
10. Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes
    - 类别级方法
    - 论文PDF：[https://arxiv.org/pdf/2508.02157](https://arxiv.org/pdf/2508.02157)
    - 代码：[https://github.com/Fischer-Tom/unified-detection-and-pose-estimation](https://github.com/Fischer-Tom/unified-detection-and-pose-estimation)
    - 是否可复现：

### NeurIPS

1. RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching
   - 类别级方法
   - 论文PDF：[https://openreview.net/pdf/93c2b32c54ac1bfa94b0ab1cd6c40361528dfee3.pdf](https://openreview.net/pdf/93c2b32c54ac1bfa94b0ab1cd6c40361528dfee3.pdf)
   - 代码：[https://github.com/shabiouyang/RMFPose](https://github.com/shabiouyang/RMFPose)
   - 是否可复现：
2. SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference
   - 任意物体方法
   - 论文PDF：[https://arxiv.org/pdf/2509.21927](https://arxiv.org/pdf/2509.21927)
   - 代码未开源
   - 是否可复现：

### AAAI

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

### MM

1. CLIP-6D: Empowering CLIP as a Zero-Shot 6D Pose Estimator Through Generalizable Object-Specific Representations
   - 类别级方法
   - 论文PDF：[https://dl.acm.org/doi/epdf/10.1145/3746027.3754497](https://dl.acm.org/doi/epdf/10.1145/3746027.3754497)
   - 代码：[https://github.com/whoawong/CLIP-6D](https://github.com/whoawong/CLIP-6D)（空仓库）
   - 是否可复现：

### ICRA

1. A Unified End-to-End Network for Category-Level and Instance-Level Object Pose Estimation from RGB Images
   - 实例级&类别级方法
   - 论文PDF：[https://ieeexplore.ieee.org/document/11128247](https://ieeexplore.ieee.org/document/11128247)
   - 代码：[https://github.com/jialeren/CIPE](https://github.com/jialeren/CIPE)（空仓库）
   - 是否可复现：
2. MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model
   - 类别级方法
   - 论文PDF：[https://arxiv.org/pdf/2504.10433](https://arxiv.org/pdf/2504.10433)
   - 代码：[https://github.com/CNJianLiu/MonoDiff9D](https://github.com/CNJianLiu/MonoDiff9D)
   - 是否可复现：
3. Occlusion-Aware 6D Pose Estimation with Depth-Guided Graph Encoding and Cross-Semantic Fusion for Robotic Grasping
   - 实例级方法
   - 论文PDF：[https://ieeexplore.ieee.org/document/11128248](https://ieeexplore.ieee.org/document/11128248)
   - 代码未开源
   - 是否可复现：

### IROS

1. 6-DoF Object Tracking with Event-based Optical Flow and Frames
   - 位姿跟踪方法
   - 论文PDF：[https://arxiv.org/pdf/2508.14776](https://arxiv.org/pdf/2508.14776)
   - 代码未开源
   - 是否可复现：
2. Distilling 3D distinctive local descriptors for 6D pose estimation
   - 实例级方法
   - 论文PDF：[https://arxiv.org/pdf/2503.15106](https://arxiv.org/pdf/2503.15106)
   - 代码：[https://github.com/tev-fbk/dGeDi/](https://github.com/tev-fbk/dGeDi/)（空仓库）
   - 是否可复现：
3. DynamicPose: Real-time and Robust 6D Object Pose Tracking for Fast-Moving Cameras and Objects
   - 位姿跟踪方法
   - 论文PDF：[https://arxiv.org/pdf/2508.11950](https://arxiv.org/pdf/2508.11950)
   - 代码：[https://github.com/Robotics-STAR-Lab/DynamicPose](https://github.com/Robotics-STAR-Lab/DynamicPose)
   - 是否可复现：
4. MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learning
   - 类别级方法
   - 论文PDF：[https://arxiv.org/pdf/2507.06662](https://arxiv.org/pdf/2507.06662)
   - 代码：[https://github.com/yangyifanYYF/MK-Pose](https://github.com/yangyifanYYF/MK-Pose)
   - 是否可复现：
5. Occlusion-Aware 6D Pose Estimation with Visual Observation Guided Diffusion Model
   - 类别级方法
   - 论文PDF：[https://ieeexplore.ieee.org/document/11247112](https://ieeexplore.ieee.org/document/11247112)
   - 代码未开源
   - 是否可复现：
6. OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB
   - 位姿跟踪方法
   - 论文PDF：[https://arxiv.org/pdf/2410.06694](https://arxiv.org/pdf/2410.06694)
   - 代码未开源
   - 是否可复现：
7. RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base
   - 实例级方法
   - 论文PDF：[https://arxiv.org/pdf/2506.18856](https://arxiv.org/pdf/2506.18856)
   - 代码：[https://github.com/SresserS/RAG-6DPose-code](https://github.com/SresserS/RAG-6DPose-code)
   - 是否可复现：
8. RCGNet: RGB-based Category-Level 6D Object Pose Estimation with Geometric Guidance
   - 类别级方法
   - 论文PDF：[https://arxiv.org/pdf/2508.13623](https://arxiv.org/pdf/2508.13623)
   - 代码未开源
   - 是否可复现：
9. RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking
   - 位姿跟踪方法
   - 论文PDF：[https://arxiv.org/pdf/2506.17119](https://arxiv.org/pdf/2506.17119)
   - 代码：[https://github.com/GreatenAnoymous/RGBTrack](https://github.com/GreatenAnoymous/RGBTrack)
   - 是否可复现：
10. Uncertainty-Aware Knowledge Distillation for Compact and Efficient 6DoF Pose Estimation
    - 实例级方法
    - 论文PDF：[https://arxiv.org/pdf/2503.13053](https://arxiv.org/pdf/2503.13053)
    - 代码未开源
    - 是否可复现：
11. VAPO: Visibility-Aware Keypoint Localization for Efficient 6DoF Object Pose Estimation
    - 实例级方法
    - 论文PDF：[https://arxiv.org/pdf/2403.14559](https://arxiv.org/pdf/2403.14559)
    - 代码：[https://github.com/RuyiLian/VAPO](https://github.com/RuyiLian/VAPO)
    - 是否可复现：

最后修改：2026 年 03 月 05 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

【论文列表】2025年Object Pose Estimation顶会论文列表

karltan0328 • 2026 年 03 月 05 日

### CVPR

### ICCV

### NeurIPS

### AAAI

### MM

### ICRA

### IROS

【论文列表】2025年Object Pose Estimation顶会论文列表

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

【环境配置】vim配置文件

【环境配置】tmux配置文件

【环境配置】Komari消息通知模板

【论文列表】2025年Object Pose Estimation顶会论文列表

【环境配置】tmux配置文件

【环境配置】vim配置文件

【论文列表】2025年Object Pose Estimation顶会论文列表

欢迎使用 Typecho

【环境配置】Komari消息通知模板

【论文列表】2025年Object Pose Estimation顶会论文列表

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。

【论文列表】2025年Object Pose Estimation顶会论文列表

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。