Research map / 3D vision / Human pose estimation
WildPose: A Unified Framework for Robust Pose Estimation in the Wild
Jianhao Zheng, Liyuan Zhu, Zihan Zhu, Iro Armeni
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 mixed static and dynamic finetuning of update operator (no motion mask) (ablation) | WildPose · Wild-SLAM MoCap | ATE RMSE (cm): 2.16 -> 0.76 | Improved |
| add mixed static and dynamic finetuning of update operator (no motion mask) (ablation) | WildPose · Bonn RGB-D Dynamic | ATE RMSE (cm): 5.58 -> 2.61 | Improved |
| add mixed static and dynamic finetuning of update operator (no motion mask) (ablation) | WildPose · TUM RGB-D dynamic | ATE RMSE (cm): 2.10 -> 1.58 | Improved |
| add motion mask detector on top of mixed finetuning (ablation) | WildPose · Wild-SLAM MoCap | ATE RMSE (cm): 0.76 -> 0.39 | Improved |
| add motion mask detector on top of mixed finetuning (ablation) | WildPose · Bonn RGB-D Dynamic | ATE RMSE (cm): 2.61 -> 2.50 | Improved |
| add motion mask detector on top of mixed finetuning (ablation) | WildPose · TUM RGB-D dynamic | ATE RMSE (cm): 1.58 -> 1.54 | Improved |
| add motion mask detector without mixed finetuning (ablation) | WildPose · Wild-SLAM MoCap | ATE RMSE (cm): 2.16 -> 0.61 | Improved |
| add motion mask detector without mixed finetuning (ablation) | WildPose · Bonn RGB-D Dynamic | ATE RMSE (cm): 5.58 -> 2.55 | Improved |
| remove depth regularizer in final global BA (ablation) | WildPose · Wild-SLAM MoCap | ATE RMSE (cm): 2.34 -> 0.39 | Improved |
| remove depth regularizer in final global BA (ablation) | WildPose · TUM RGB-D dynamic | ATE RMSE (cm): 2.13 -> 1.54 | Improved |
| remove depth regularizer in final global BA (ablation) | WildPose · Bonn RGB-D Dynamic | ATE RMSE (cm): 2.60 -> 2.50 | Improved |
| replace WildGS-SLAM per-sequence mask training with WildPose on short sequences | WildPose · Sintel | ATE RMSE: 0.049 -> 0.017 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- MegaSaM — MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos (CVPR 2025) · better on 6 of 6 shared results
- WildGS-SLAM — WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments (CVPR 2025) · better on 4 of 5 shared results
- DROID-SLAM — DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (NeurIPS 2021) · better on 4 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
- MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos (CVPR 2025 · similarity 0.89)
- WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild (NeurIPS 2025 · similarity 0.87)
- WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments (CVPR 2025 · similarity 0.87)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.87)
- HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset (CVPR 2025 · similarity 0.87)
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image (CVPR 2025 · similarity 0.86)
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.
