AI Paper Atlas

Research map / 3D vision / Human pose estimation

NeMo: Learning 3D Neural Motion Fields From Multiple Video Instances of the Same Action

Kuan-Chieh Wang, Zhenzhen Weng, Maria Xenochristou, João Pedro Araújo, Jeffrey Gu, Karen Liu, Serena Yeung

CVPR 2023 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 8 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
Jointly optimize multiple video instances of the same action with NeMoVIBE-initialized HMR on the MoCap dataset · MoCap dataset, mean dynamic rangeMPJPE (mm): 120.5 mm to 95.5 mmImproved
Use NeMo to jointly recover global root motionGlobal HMR on the MoCap dataset · MoCap dataset, meanGlobal-MPJPE (mm): 141 mm to 127 mmImproved
Jointly optimize multiple video instances of the same actionHMR on Penn Action · Penn Action, mean2D reconstruction error (pixels): 11.2 to 8.1Improved
Apply SMPLify test-time optimization to VIBEVIBE on the MoCap dataset · MoCap dataset, mean dynamic rangeMPJPE (mm): 120.5 / 132.3Hurt
Add 3D supervision from initial HMR estimates (ablation)NeMo on the MoCap dataset · MoCap datasetMPJPE: 125.22 -> 77.96Improved
Add 3D supervision from initial HMR estimates (ablation)NeMo on the MoCap dataset · MoCap dataset, dynamic rangeMPJPE: 161.82 -> 95.7Improved
Add 3D supervision from initial HMR estimates (ablation)NeMo on the MoCap dataset · MoCap dataset2D PCK: 98.4 -> 99.08Improved
Add instance-specific learnable parameters (ablation)NeMo on the MoCap dataset · MoCap datasetMPJPE: 134.85 -> 77.96Improved
Add instance-specific learnable parameters (ablation)NeMo on the MoCap dataset · MoCap dataset, dynamic rangeMPJPE: 194.6 -> 95.7Improved
Add instance-specific learnable parameters (ablation)NeMo on the MoCap dataset · MoCap dataset2D PCK: 89.57 -> 99.08Improved

Later papers that compared with this method

1 later accepted paper reports NeMo as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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