Research map / 3D vision / Human pose estimation
gDLS*: Generalized Pose-and-Scale Estimation Given Scale and Gravity Priors
Victor Fragoso, Joseph DeGol, Gang Hua
Check 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 a gravity-direction rotation prior (ablation) | gDLS* · TUM and KITTI trajectory registration | rotation error | Improved |
| Add a gravity-direction rotation prior (ablation) | gDLS* · TUM and KITTI trajectory registration | estimation time | Improved |
| Add a scale prior (ablation) | gDLS* · TUM and KITTI trajectory registration | scale error | Improved |
| Add a scale prior (ablation) | gDLS* · TUM and KITTI trajectory registration | translation error | Improved |
| Add both scale and gravity priors (ablation) | gDLS* · TUM and KITTI trajectory registration | scale error | Improved |
| Increase noise in the gravity prior | gDLS* · Synthetic data | accuracy | No clear effect |
| Increase noise in the scale prior | gDLS* · Synthetic data | accuracy | Hurt |
| Use non-minimal samples instead of four correspondences | gDLS* variants · Synthetic data | rotation, translation, and scale errors | Improved |
| Use prior-regularized gDLS* rather than gP+s | Synthetic data estimators · Synthetic data | rotation and translation errors | Improved |
Later papers that compared with this method
1 later accepted paper reports gDLS+++ as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Scene Grounding in the Wild (CVPR 2026 · better on 3 of 4 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
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.86)
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · similarity 0.85)
- Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences (CVPR 2024 · similarity 0.85)
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation (CVPR 2025 · similarity 0.84)
- Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis (NeurIPS 2024 · similarity 0.84)
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image (CVPR 2025 · similarity 0.84)
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.
