AI Paper Atlas

Research map / 3D vision / Human pose estimation

EgoM2P: Egocentric Multimodal Multitask Pretraining

Gen Li, Yutong Chen, Yiqian Wu, Kaifeng Zhao, Marc Pollefeys, Siyu Tang

ICCV 2025 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 4 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
add EgoGen synthetic data to training (ablation)EgoM2P · EgoExo4D camera trackingATE: 0.028 -> 0.017Improved
add EgoGen synthetic data to training (ablation)EgoM2P · ADT camera tracking (unseen)RRE: 0.593 -> 0.490Improved
add EgoGen synthetic data to training (ablation)EgoM2P · H2O video depthAbs Rel: 0.062 -> 0.055Improved
add EgoGen synthetic data to training (ablation)EgoM2P · HOI4D video depth (unseen)delta 1.25: 97.1 -> 98.0Improved
increase max visible input/target tokens from 1024 to 2048 (ablation)EgoM2P pretraining · Pretraining validationavg loss: 5.80 -> 4.93Improved
sample datasets proportional to size instead of uniform or log-size (ablation)EgoM2P pretraining · validation loss across datasetsvalidation lossImproved
post-train on unseen ADT training setEgoM2P · ADT camera tracking (unseen)ATE: 0.032 -> 0.026Improved
post-train on unseen HOI4D training setEgoM2P · HOI4D video depth (unseen)Abs Rel: 0.061 -> 0.041Improved
post-train on unseen ASE training setEgoM2P · ASE depth-to-RGB synthesis (unseen)FVD/10^3: 1.336 -> 0.525Improved
EgoM2P versus test-time-optimization camera trackers on speedEgoM2P · Camera tracking runtime per sequencetime: 2.7s -> 0.18sImproved

Later papers that compared with this method

1 later accepted paper reports EgoM2P 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 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