AI Paper Atlas

Research map / 3D vision / Human pose estimation

Reconstructing NBA Players

Luyang Zhu, Konstantinos Rematas, Brian Curless, Steven M. Seitz, Ira Kemelmacher-Shlizerman

ECCV 2020 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 41 citations (OpenAlex)

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 changedWhereMeasuredEffect
use location-map representation instead of direct 3D joint regression (ablation)PoseNet with bone length loss · NBA2K 3D poseMPJPE: 81.66 -> 51.67Improved
use location-map representation instead of direct 3D joint regression (ablation)PoseNet with bone length loss · NBA2K 3D poseMPJPE-PA: 63.70 -> 40.91Improved
add bone length loss (ablation)PoseNet with location maps · NBA2K 3D poseMPJPE: 66.12 -> 51.67Improved
add bone length loss (ablation)PoseNet with location maps · NBA2K 3D poseMPJPE-PA: 52.73 -> 40.91Improved
use PoseNet instead of fine-tuned SPINpose estimation · NBA2K 3D poseMPJPE: 88.72 -> 51.67Improved
use SkinningNet instead of 3D-CODEDmesh deformation · NBA2K meshMPVPE (mm): 84.22 -> 76.41Improved
use SkinningNet instead of CMRmesh deformation · NBA2K meshMPVPE-PA (mm): 64.32 -> 54.71Improved
use full pipeline instead of PIFu retrained on NBA2Kmesh reconstruction · NBA2K meshChamfer distance: 23.136 -> 4.934Improved
use SkinningNet instead of SMPL-NBA skinning model (ablation)mesh deformation · NBA2K qualitativevisual qualityImproved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy