Research map / Point clouds / Registration and matching
SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation
Haobo Jiang, Mathieu Salzmann, Zheng Dang, Jin Xie, Jian Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| wrap DCP in SE(3) diffusion framework (Diff-DCP) | DCP · LINEMOD | 5deg mAP: 0.06 -> 0.22 | Improved |
| wrap DCP in SE(3) diffusion framework (Diff-DCP) | DCP · TUD-L | 1cm mAP: 0.04 -> 0.73 | Improved |
| wrap RPMNet in SE(3) diffusion framework (Diff-RPMNet) | RPMNet · TUD-L | 5deg mAP: 0.73 -> 0.90 | Improved |
| wrap RPMNet in SE(3) diffusion framework (Diff-RPMNet) | RPMNet · Occluded-LINEMOD | 5deg mAP: 0.03 -> 0.12 | Improved |
| add diffusion-generated pose augmentation (DiffAug) to training (ablation) | DCP · LINEMOD | 1cm mAP: 0.11 -> 0.52 | Improved |
| add reverse denoising process on top of DiffAug (ablation) | DCP+DiffAug · LINEMOD | 1cm mAP: 0.52 -> 0.65 | Improved |
| use cosine instead of linear noise schedule (ablation) | Diff-DCP · LINEMOD | 1cm mAP: 0.56 -> 0.65 | Improved |
| use cosine instead of linear noise schedule (ablation) | Diff-DCP · TUD-L | 1cm mAP: 0.93 -> 0.73 | Hurt |
| use deterministic instead of random inference (ablation) | Diff-DCP · LINEMOD | 1cm mAP: 0.62 -> 0.65 | Improved |
| increase diffusion steps from 50 to 200 (ablation) | Diff-DCP · LINEMOD | 1cm mAP: 0.54 -> 0.65 | Improved |
| increase diffusion steps from 100 to 200 (ablation) | Diff-DCP · TUD-L | 1cm mAP: 0.87 -> 0.73 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RPMNet — RPM-Net: Robust Point Matching Using Learned Features (CVPR 2020) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Where Precision Meets Efficiency: Transformation Diffusion Model for Point Cloud Registration (AAAI 2025 · similarity 0.92)
- 6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation (CVPR 2024 · similarity 0.90)
- Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3) (CVPR 2024 · similarity 0.89)
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.88)
- Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates (NeurIPS 2025 · similarity 0.88)
- Multiway Point Cloud Mosaicking with Diffusion and Global Optimization (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
