Research map / 3D vision / Human pose estimation
HoloPose: Holistic 3D Human Reconstruction In-The-Wild
Riza Alp Guler, Iasonas Kokkinos
Check 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 |
|---|---|---|---|
| Apply synergistic refinement to the HoloPose estimate | HoloPose · DensePose | AUC10: 0.24 -> 0.29 | Improved |
| Apply synergistic refinement to the HoloPose estimate | HoloPose · DensePose | FR10: 51.1 -> 44.6 | Improved |
| Use the DensePose branch prediction instead of mesh reprojection | HoloPose · DensePose | AUC10: 0.24 -> 0.40 | Improved |
| Use the DensePose branch prediction instead of mesh reprojection | HoloPose · DensePose | FR10: 51.1 -> 32.0 | Improved |
| Apply synergistic refinement to the HoloPose estimate | HoloPose · Human3.6M Protocol 1 | PA MPJPE: 50.56 -> 46.52 | Improved |
| Apply synergistic refinement to the HoloPose estimate | HoloPose · Human3.6M Protocol 2 | MPJPE: 64.28 -> 60.27 | Improved |
| Add the 2D keypoint loss alone during refinement (ablation) | HoloPose · DensePose refinement ablation | FR10: 51.1 -> 45.8 | Improved |
| Add the 2D keypoint loss alone during refinement (ablation) | HoloPose · 3D keypoint refinement ablation | PA MPJPE: 50.56 -> 52.32 | Hurt |
| Add the 3D keypoint loss alone during refinement (ablation) | HoloPose · DensePose refinement ablation | FR10: 51.1 -> 52.3 | Hurt |
| Add the 3D keypoint loss alone during refinement (ablation) | HoloPose · 3D keypoint refinement ablation | PA MPJPE: 50.56 -> 46.78 | Improved |
| Add the DensePose loss alone during refinement (ablation) | HoloPose · DensePose refinement ablation | FR10: 51.1 -> 43.3 | Improved |
| Add the DensePose loss alone during refinement (ablation) | HoloPose · 3D keypoint refinement ablation | PA MPJPE: 50.56 -> 56.87 | Hurt |
Later papers that compared with this method
1 later accepted paper reports HoloPose as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Learning 3D Human Shape and Pose from Dense Body Parts (TPAMI 2020 · 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
- UltraPose: Synthesizing Dense Pose With 1 Billion Points by Human-Body Decoupling 3D Model (ICCV 2021 · similarity 0.89)
- HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models (CVPR 2024 · similarity 0.88)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.87)
- SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction (NeurIPS 2025 · similarity 0.87)
- Reconstructing Humans with a Biomechanically Accurate Skeleton (CVPR 2025 · similarity 0.87)
- GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data (NeurIPS 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.
