Research map / 3D vision / Human pose estimation
DECA: Deep Viewpoint-Equivariant Human Pose Estimation Using Capsule Autoencoders
Nicola Garau, Niccolò Bisagno, Piotr Bródka, Nicola Conci
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 inverse graphics loss W (ablation) | DECA-D1 · ITOP top-view | mean mAP @0.1m: 83.85 -> 85.58 | Improved |
| add 2D joint prediction task (ablation) | DECA-D2 · ITOP top-view | mean mAP @0.1m: 85.58 -> 86.92 | Improved |
| add inverse graphics loss W (ablation) | DECA-D1 · ITOP top-view lower body | mAP @0.1m: 89.96 -> 91.27 | Improved |
| add 2D joint prediction task (ablation) | DECA-D2 · ITOP top-view hands | mAP @0.1m: 45.97 -> 54.33 | Improved |
| add inverse graphics loss W (ablation) | DECA-D1 · ITOP top-view hands | mAP @0.1m: 44.41 -> 45.97 | Improved |
| add 2D joint prediction task (ablation) | DECA-D2 · ITOP top-view shoulders | mAP @0.1m: 97.51 -> 96.57 | Hurt |
| add 2D joint prediction task (ablation) | DECA-D2 · ITOP top-view feet | mAP @0.1m: 83.53 -> 81.88 | Hurt |
| use DECA-D3 versus V2V | DECA-D3 · ITOP top-view | mean mAP @0.1m: 83.44 -> 86.92 | Improved |
| use DECA-D3 versus V2V | DECA-D3 · ITOP front-view | mean mAP @0.1m: 88.74 -> 88.75 | No clear effect |
| use DECA-D3 versus V2V | DECA-D3 · ITOP front-view hands | mAP @0.1m: 67.26 -> 56.49 | Hurt |
| use DECA-D3 versus best prior on viewpoint transfer | DECA-D3 · ITOP train front test top | full-body mAP @0.1m: 20.40 -> 51.85 | Improved |
| apply Procrustes alignment to predicted poses (ablation) | DECA-R4 · PanopTOP31K train front test front | MPJPE (mm): 7.16 -> 5.15 | Improved |
Closest papers by meaning
- EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks (ICCV 2025 · similarity 0.88)
- A Simple yet Effective Baseline for 3D Human Pose Estimation (ICCV 2017 · similarity 0.88)
- 3D Human Pose Estimation From a Single Image via Distance Matrix Regression (CVPR 2017 · similarity 0.88)
- Towards Viewpoint Invariant 3D Human Pose Estimation (ECCV 2016 · similarity 0.88)
- Coarse-To-Fine Volumetric Prediction for Single-Image 3D Human Pose (CVPR 2017 · similarity 0.87)
- PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization (CVPR 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.
