Research map / 3D vision / Human pose estimation
6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting
Yufeng Jin, Vignesh Prasad, Snehal Jauhri, Mathias Franzius, Georgia Chalvatzaki
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 |
|---|---|---|---|
| add dynamic keyframe selection (ablation) | 6DOPE-GS · HO3D | ADD (%): 82.40 -> 84.33 | Improved |
| add dynamic keyframe selection (ablation) | 6DOPE-GS · YCBInEOAT | ADD (%): 86.40 -> 87.82 | Improved |
| add dynamic keyframe selection (ablation) | 6DOPE-GS · HO3D | ADD-S (%): 94.44 -> 95.07 | Improved |
| add opacity-percentile adaptive density control (ablation) | 6DOPE-GS · HO3D | ADD-S (%): 92.48 -> 95.07 | Improved |
| add opacity-percentile adaptive density control (ablation) | 6DOPE-GS · HO3D | ADD (%): 80.87 -> 84.33 | Improved |
| add opacity-percentile adaptive density control (ablation) | 6DOPE-GS · YCBInEOAT | ADD (%): 86.22 -> 87.82 | Improved |
| use 2D Gaussians instead of 3D Gaussians (ablation) | 6DOPE-GS · HO3D | ADD (%): 79.49 -> 84.33 | Improved |
| use 2D Gaussians instead of 3D Gaussians (ablation) | 6DOPE-GS · YCBInEOAT | Chamfer distance (cm): 0.41 -> 0.15 | Improved |
| add both keyframe selection and pruning to basic version (ablation) | 6DOPE-GS · HO3D | ADD (%): 80.25 -> 84.33 | Improved |
| replace BundleSDF neural object field with Gaussian object field | BundleSDF · HO3D | avg time per frame (s): 2.10 -> 0.24 | Improved |
| replace BundleSDF with 6DOPE-GS | BundleSDF · HO3D | ADD (%): 89.56 -> 84.33 | Hurt |
| replace BundleSDF with 6DOPE-GS | BundleSDF · HO3D | Chamfer distance (cm): 0.58 -> 0.41 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- BundleSDF — BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects (CVPR 2023) · better on 7 of 8 shared results
- DROID-SLAM — DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (NeurIPS 2021) · better on 2 of 2 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
- iG-6DoF: Model-free 6DoF Pose Estimation for Unseen Object via Iterative 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- 6D Object Pose Tracking in Internet Videos for Robotic Manipulation (ICLR 2025 · similarity 0.88)
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.88)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.87)
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · similarity 0.87)
- Gaussian Splatting SLAM (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.
