AI Paper Atlas

Research map / 3D vision / 3D generation

EgoMAN: Interaction-Structured Reasoning for Egocentric 3D Hand Trajectory Prediction

Mingfei Chen, Yifan Wang, Zhengqin Li, Homanga Bharadhwaj, Yujin Chen, Chuan Qin, Ziyi Kou, Yuan Tian, Eric Whitmire, Rajinder Sodhi, Hrvoje Benko, Eli Shlizerman and 1 more

ECCV 2026 · 3D vision › 3D generation · approach: Hand-object interaction generation · 0 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 6DoF Trajectory-Token Interface waypoints (ablation)EgoMAN · EgoMAN-Unseen (K=1) ablationADE: 0.161 -> 0.151Improved
add 6DoF Trajectory-Token Interface waypoints (ablation)EgoMAN · EgoMAN-Unseen (K=1) ablationDTW: 0.147 -> 0.137Improved
add 6DoF Trajectory-Token Interface waypoints (ablation)EgoMAN · EgoMAN-Unseen (K=1) ablationRotation error: 35.90 -> 33.88Improved
add interaction-structured reasoning without waypoints (ablation)EgoMAN · EgoMAN-Unseen (K=1) ablationADE: 0.162 -> 0.161No clear effect
add Motion Expert pretraining (ablation)EgoMAN · EgoMAN-Unseen (K=1) ablationADE: 0.215 -> 0.150Improved
add reasoning and Motion Expert pretraining (ablation)EgoMAN · EgoMAN-Unseen (K=1) ablationADE: 0.273 -> 0.151Improved
use 6DoF waypoints instead of decoder hidden state (Emb) (ablation)EgoMAN · EgoMAN-Unseen (K=1) ablationFDE: 0.210 -> 0.206No clear effect
add interaction-structured reasoning (ablation)EgoMAN · EgoMAN-Unseen (K=10)ADE: 0.141 -> 0.124Improved
add interaction-structured reasoning (full data) (ablation)EgoMAN · EgoMAN-Unseen data efficiencyADE: 0.140 -> 0.125Improved
add interaction-structured reasoning (20% data) (ablation)EgoMAN · EgoMAN-Unseen data efficiencyADE: 0.16 -> 0.13Improved
use Flow Matching Motion Expert instead of MMTwin*FM-base · EgoMAN-Unseen (K=10)ADE: 0.206 -> 0.160Improved
use EgoMAN instead of HandsOnVLM*EgoMAN · EgoMAN-Unseen (K=10)ADE: 0.171 -> 0.124Improved

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