Research map / 3D vision / Human pose estimation
Reconstructing NBA Players
Luyang Zhu, Konstantinos Rematas, Brian Curless, Steven M. Seitz, Ira Kemelmacher-Shlizerman
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 location-map representation instead of direct 3D joint regression (ablation) | PoseNet with bone length loss · NBA2K 3D pose | MPJPE: 81.66 -> 51.67 | Improved |
| use location-map representation instead of direct 3D joint regression (ablation) | PoseNet with bone length loss · NBA2K 3D pose | MPJPE-PA: 63.70 -> 40.91 | Improved |
| add bone length loss (ablation) | PoseNet with location maps · NBA2K 3D pose | MPJPE: 66.12 -> 51.67 | Improved |
| add bone length loss (ablation) | PoseNet with location maps · NBA2K 3D pose | MPJPE-PA: 52.73 -> 40.91 | Improved |
| use PoseNet instead of fine-tuned SPIN | pose estimation · NBA2K 3D pose | MPJPE: 88.72 -> 51.67 | Improved |
| use SkinningNet instead of 3D-CODED | mesh deformation · NBA2K mesh | MPVPE (mm): 84.22 -> 76.41 | Improved |
| use SkinningNet instead of CMR | mesh deformation · NBA2K mesh | MPVPE-PA (mm): 64.32 -> 54.71 | Improved |
| use full pipeline instead of PIFu retrained on NBA2K | mesh reconstruction · NBA2K mesh | Chamfer distance: 23.136 -> 4.934 | Improved |
| use SkinningNet instead of SMPL-NBA skinning model (ablation) | mesh deformation · NBA2K qualitative | visual quality | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- 3D-CODED — 3D-CODED: 3D Correspondences by Deep Deformation (ECCV 2018) · 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
- End-to-End Camera Calibration for Broadcast Videos (CVPR 2020 · similarity 0.84)
- Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing (ICCV 2023 · similarity 0.83)
- Accurate 3D Body Shape Regression Using Metric and Semantic Attributes (CVPR 2022 · similarity 0.83)
- 3DPeople: Modeling the Geometry of Dressed Humans (ICCV 2019 · similarity 0.83)
- Egocentric Basketball Motion Planning From a Single First-Person Image (CVPR 2018 · similarity 0.83)
- BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation (CVPR 2025 · similarity 0.83)
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.
