AI Paper Atlas

Research map / 3D vision / Human pose estimation

EgoMo3R: Joint Egocentric Motion and Scene Reconstruction

Chaitanya Patel, Yusuke Kato, Rin Takahira, Kazuki Kozuka, Juan Carlos Niebles, Ehsan Adeli

NeurIPS 2026 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes EgoMo3R, a method that jointly reconstructs egocentric 3D human motion and the surrounding scene from egocentric video, rather than treating the two tasks separately.

Problem

Egocentric 3D human motion reconstruction usually assumes metric, gravity-aligned camera trajectories from inertial sensors, and scene reconstruction is handled separately even though the two tasks are coupled.

Approach

Treats egocentric motion and scene reconstruction as a single coupled problem solved jointly from video, removing the need for specialized inertial sensors to obtain metric, gravity-aligned camera trajectories.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add point-track loss to flow-only optimization (ablation)EgoMo3R scene-only · EgoExo4D locomotionATE: 0.604 -> 0.361Improved
add depth-scale regularizer L_depth (ablation)EgoMo3R scene-only · EgoExo4D locomotionATE: 0.361 -> 0.353Improved
add floor coplanarity loss L_scene (ablation)EgoMo3R scene-only · EgoExo4D locomotionATE: 0.353 -> 0.371 (Acc mean 0.414 -> 0.398)Mixed
add motion prior with direct joint optimization (ablation)EgoMo3R · EgoExo4D locomotionMPJPE: MPJPE 0.456Hurt
use alternating instead of direct optimization of motion prior (ablation)EgoMo3R · EgoExo4D locomotionMPJPE: 0.456 -> 0.320Improved
use alternating instead of direct optimization (ablation)EgoMo3R · EgoExo4D locomotionATE: 0.350 -> 0.318Improved
replace motion prior with camera-smoothness prior (ablation)EgoMo3R · EgoExo4D locomotionATE: 0.318 -> 0.335Hurt
replace motion prior with camera-smoothness prior (ablation)EgoMo3R · EgoExo4D locomotionRPE Trans: 0.095 -> 0.074Improved
add a third alternation round (ablation)EgoMo3R · EgoExo4D locomotionATE: 0.318 -> 0.300Improved
warm-start camera trajectory with flow-only optimization before full objectiveEgoMo3R · EgoExo4Dtrajectory stabilityImproved
use EgoMo3R joint optimization instead of CUT3R/ViPE trajectory + EgoAlloEgoMo3R · EgoExo4DMPJPE: 0.348 -> 0.271Improved
use weaker point tracker or depth model (ablation)EgoMo3R scene-only · EgoExo4D locomotionATEHurt

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