Research map / 3D vision / Human pose estimation
"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization"
Muhammad Zubair Irshad, Sergey Zakharov, Rareș Ambruș, Thomas Kollar, Zsolt Kira, Adrien Gaidon
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 |
|---|---|---|---|
| use ShAPO instead of CenterSnap-R | ShAPO · REAL275 | 5deg 10cm mAP: 31.6 -> 57.0 | Improved |
| use ShAPO instead of CenterSnap-R | ShAPO · REAL275 | 10deg 10cm mAP: 70.9 -> 78.0 | Improved |
| use ShAPO instead of CenterSnap-R | ShAPO · CAMERA25 | 5deg 10cm mAP: 71.7 -> 75.9 | Improved |
| use ShAPO instead of CenterSnap-R | ShAPO · REAL275 | IOU50 mAP: 80.2 -> 79.0 | Hurt |
| use ShAPO shape optimization instead of baseline reconstruction | ShAPO · NOCS reconstruction | mean chamfer distance (CAMERA25): 0.20 -> 0.14 | Improved |
| use ShAPO shape optimization instead of baseline reconstruction | ShAPO · NOCS reconstruction | mean chamfer distance (REAL275): 0.32 -> 0.15 | Improved |
| add differentiable optimization of texture latent (ablation) | ShAPO · NOCS REAL275 | texture PSNR: 11.41 -> 20.64 | Improved |
| add fine-tuning of texture network weights after optimization (ablation) | ShAPO · NOCS REAL275 | texture PSNR: 20.64 -> 24.32 | Improved |
| use octree sampling LoD6 instead of ordinary grid 60 (ablation) | ShAPO · NOCS reconstruction | time (s): 30.51 -> 6.88 | Improved |
| use octree sampling LoD6 instead of ordinary grid 60 (ablation) | ShAPO · NOCS reconstruction | GPU memory (MB): 7850 -> 2880 | Improved |
| use octree sampling LoD6 instead of ordinary grid 60 (ablation) | ShAPO · NOCS reconstruction | texture PSNR: 19.52 -> 13.63 | Hurt |
| raise octree level from LoD6 to LoD7 (ablation) | ShAPO · NOCS reconstruction | texture PSNR: 13.63 -> 16.14 | Improved |
Later papers that compared with this method
1 later accepted paper reports ShAPO as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation (TPAMI 2025 · better on 2 of 2 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
- BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects Without Using Depth (ICCV 2017 · similarity 0.87)
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image (CVPR 2025 · similarity 0.86)
- Learning Category-Specific Deformable 3D Models for Object Reconstruction (TPAMI 2016 · similarity 0.86)
- AlignPose: Generalizable 6D Pose Estimation via Multi-view Feature-metric Alignment (CVPR 2026 · similarity 0.86)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.85)
- NOPE: Novel Object Pose Estimation from a Single Image (CVPR 2024 · similarity 0.85)
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.
