Research map / 3D vision / Human pose estimation
LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation
Ruida Zhang, Ziqin Huang, Gu Wang, Chenyangguang Zhang, Yan Di, Xingxing Zuo, Jiwen Tang, Xiangyang Ji
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 scale-agnostic pose representation (ablation) | LaPose (conv stream) · NOCS-REAL275 | NIoU25: 37.8 -> 60.3 | Improved |
| add DINOv2 stream to conv stream (ablation) | LaPose · NOCS-REAL275 | NIoU25: 60.3 -> 64.9 | Improved |
| use DINOv2 features alone instead of conv features (ablation) | LaPose · NOCS-REAL275 | NIoU50: 39.7 -> 26.9 | Hurt |
| model NOCS as Laplacian distribution and feed variance to PnP (ablation) | LaPose (conv stream) · NOCS-REAL275 | NIoU25: 60.3 -> 65.5 | Improved |
| model NOCS as Gaussian instead of Laplacian (ablation) | LaPose (conv stream) · NOCS-REAL275 | NIoU25: 60.3 -> 59.1 | Hurt |
| extend two-stream model to Laplacian mixture (ablation) | LaPose · NOCS-REAL275 | NIoU50: 42.1 -> 47.9 | Improved |
| train separate model per category (LaPose M) instead of single model | LaPose · NOCS-REAL275 (scale-agnostic) | NIoU75: 15.8 -> 20.5 | Mixed |
| LaPose versus DMSR on NOCS-CAMERA25 | LaPose · NOCS-CAMERA25 | NIoU75: 11.1 -> 14.1 | Improved |
Later papers that compared with this method
2 later accepted papers report LaPose as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation (CVPR 2025 · better on 17 of 17 shared results)
- Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes (ICCV 2025 · better on 16 of 17 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
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.89)
- GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.88)
- Rethinking Correspondence-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.87)
- HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation (CVPR 2024 · similarity 0.86)
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation (CVPR 2024 · similarity 0.86)
- MFOS: Model-Free & One-Shot Object Pose Estimation (AAAI 2024 · 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.
