Research map / 3D vision / Human pose estimation
Towards Real-World Aerial Vision Guidance With Categorical 6D Pose Tracker
Jingtao Sun, Yaonan Wang, Danwei Wang
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 weight-shared attention (WAS) (ablation) | Robust6DoF baseline M0 · NOCS-REAL275 | 5deg2cm: 30.1 -> 33.2 | Improved |
| add global dense fusion (GDF) (ablation) | Robust6DoF with WAS · NOCS-REAL275 | 5deg2cm: 33.2 -> 33.5 | Improved |
| add spatial-temporal filtering encoder (STE) (ablation) | Robust6DoF with WAS+GDF · NOCS-REAL275 | 5deg2cm: 33.5 -> 50.4 | Improved |
| add shape-similarity filtering (SSF) (ablation) | Robust6DoF with WAS+GDF+STE · NOCS-REAL275 | 5deg2cm: 50.4 -> 55.4 | Improved |
| add augmentation decoder (AD) (ablation) | Robust6DoF with WAS+GDF+STE+SSF · NOCS-REAL275 | 5deg2cm: 55.4 -> 57.1 | Improved |
| add augmentation decoder (AD) (ablation) | Robust6DoF with WAS+GDF+STE+SSF · NOCS-REAL275 | IoU25: 90.2 -> 89.8 | Hurt |
| add prior guidance (ablation) | Robust6DoF · NOCS-REAL275 | 5deg5cm: 35.9 -> 70.6 | Improved |
| add finer matching (ablation) | Robust6DoF · NOCS-REAL275 | 5deg5cm: 62.5 -> 70.6 | Improved |
| use proposed keypoint generation instead of unsupervised keypoints (ablation) | Robust6DoF · NOCS-REAL275 | 5deg5cm: 63.0 -> 70.6 | Improved |
| add prior guidance (ablation) | Robust6DoF · Wild6D | IoU50: 65.2 -> 75.1 | Improved |
| add finer matching (ablation) | Robust6DoF · Wild6D | 5deg5cm: 43.2 -> 44.4 | Improved |
| use proposed keypoint generation instead of unsupervised keypoints (ablation) | Robust6DoF · Wild6D | 5deg5cm: 40.1 -> 44.4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- Query6DoF — Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose Estimation (ICCV 2023) · better on 3 of 3 shared results
- IST-Net — IST-Net: Prior-Free Category-Level Pose Estimation with Implicit Space Transformation (ICCV 2023) · better on 3 of 3 shared results
- CAPTRA — CAPTRA: CAtegory-Level Pose Tracking for Rigid and Articulated Objects From Point Clouds (ICCV 2021) · better on 3 of 3 shared results
- TEASER — TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction (ICLR 2025) · better on 1 of 1 shared result
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
- ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation (NeurIPS 2026 · similarity 0.84)
- 6D Object Pose Tracking in Internet Videos for Robotic Manipulation (ICLR 2025 · similarity 0.84)
- Vision Foundation Model Enables Generalizable Object Pose Estimation (NeurIPS 2024 · similarity 0.83)
- Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking (CVPR 2025 · similarity 0.83)
- DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation (NeurIPS 2026 · similarity 0.83)
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · similarity 0.83)
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.
