Research map / 3D vision / Human pose estimation
ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use ES6D rather than DenseFusion (iterative) | YCB-Video with PoseCNN masks · YCB-Video | ADD-S: 93.2 -> 93.6 | Helped |
| Use ES6D rather than PVN3D | YCB-Video with GT masks · YCB-Video | ADD(S): 91.9 -> 93.2 | Helped |
| Use ES6D rather than StablePose | T-LESS · T-LESS | e_VSD (SISO): 0.73 -> 0.76 | Helped |
| Use ES6D rather than StablePose | T-LESS · T-LESS | e_ADI (SISO): 0.88 -> 0.82 | Hurt |
| Add spatial information encoding (ablation) | XYZNet_1 · YCB-Video | ADD(S): 91.86 -> 92.04 | Helped |
| Concatenate the XYZ map with local features (ablation) | XYZNet_2 · YCB-Video | ADD(S): 92.04 -> 92.42 | Helped |
| Add feature aggregation (ablation) | XYZNet_3 · YCB-Video | ADD(S): 92.42 -> 93.03 | Helped |
| Train with A(M)GPD loss instead of ADD(S) loss (ablation) | ES6D · T-LESS | A(M)GPD: 55.99 -> 82.70 | Helped |
| Train with A(M)GPD loss instead of ADD(S) loss (ablation) | ES6D · T-LESS | ADD(S): 93.08 -> 93.40 | Helped |
Closest papers by meaning
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.88)
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.88)
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · similarity 0.87)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.87)
- GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.87)
- CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image (CVPR 2025 · 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.