Research map / 3D vision / Human pose estimation
Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Network
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 |
|---|---|---|---|
| generate multiple 3D pose hypotheses with an MDN instead of a single estimate | 2D-to-3D pose estimation · Human3.6M Protocol #1 | MPJPE (mm): 55.8 -> 52.7 | Helped |
| use multi-view images to select and average consistent pose hypotheses | MDN pose estimator · Human3.6M multi-view | MPJPE (mm): 51.9 -> 49.6 | Helped |
| generate multiple 3D pose hypotheses with an MDN | 2D-to-3D pose estimation with missing joints · Human3.6M one missing joint | MPJPE (mm): 69.1 -> 58.8 | Helped |
| generate multiple 3D pose hypotheses with an MDN | 2D-to-3D pose estimation with missing joints · Human3.6M two missing joints | MPJPE (mm): 75.1 -> 64.6 | Helped |
| transfer the Human3.6M-trained model to MPI-INF-3DHP | MDN pose estimator · MPI-INF-3DHP All | 3DPCK: 72.5 -> 67.9 | Hurt |
| use an MDN instead of a single-Gaussian estimate (ablation) | Human3.6M pose estimation · Human3.6M | MPJPE (mm): 62.9 -> 52.7 | Helped |
| increase the kernel count from 3 to 5 (ablation) | MDN pose estimator · Human3.6M | MPJPE (mm): 55.2 -> 52.7 | Helped |
| increase the kernel count from 5 to 8 (ablation) | MDN pose estimator · Human3.6M | MPJPE (mm): 52.7 -> 52.6 | No clear effect |
| add a Dirichlet prior to the mixture coefficients (ablation) | MDN pose estimator · Human3.6M | MPJPE (mm): 53.7 -> 52.7 | Helped |
Closest papers by meaning
- Sparseness Meets Deepness: 3D Human Pose Estimation From Monocular Video (CVPR 2016 · similarity 0.91)
- 3D Human Pose Estimation From a Single Image via Distance Matrix Regression (CVPR 2017 · similarity 0.90)
- ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation (NeurIPS 2024 · similarity 0.89)
- PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization (CVPR 2024 · similarity 0.88)
- ProPose: Probabilistic 3D Human Pose Estimation with Instance-Level Distribution and Normalizing Flow (AAAI 2025 · similarity 0.88)
- CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators (ICLR 2025 · similarity 0.88)
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.