AI Paper Atlas

Research map / 3D vision / 3D generation

UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation

Chaitanya Patel, Hiroki Nakamura, Yuta Kyuragi, Kazuki Kozuka, Juan Carlos Niebles, Ehsan Adeli

ICCV 2025 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 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
use head-centric instead of pelvis-centric motion representation (ablation)UniEgoMotion · EE4D-Motion reconstructionMPJPE: 0.166 -> 0.100Improved
use head-centric instead of pelvis-centric motion representation (ablation)UniEgoMotion · EE4D-Motion reconstructionHead Trans. Err.: 0.138 -> 0.058Improved
use head-centric instead of global motion representation (ablation)UniEgoMotion · EE4D-Motion forecastingMPJPE 2-4s: 0.293 -> 0.206Improved
use head-centric instead of global motion representation (ablation)UniEgoMotion · EE4D-Motion reconstructionHead Trans. Err.: 0.051 -> 0.058Hurt
use transformer decoder instead of transformer encoder (ablation)UniEgoMotion · EE4D-Motion reconstructionFoot Slide: 4.48 -> 3.62Improved
use transformer decoder instead of 1D U-Net (ablation)UniEgoMotion · EE4D-Motion reconstructionMPJPE: 0.145 -> 0.100Improved
use transformer decoder instead of 1D U-Net (ablation)UniEgoMotion · EE4D-Motion generationMPJPE 0-2s: 0.259 -> 0.226Improved
use DINOv2 instead of CLIP image encoder (ablation)UniEgoMotion · EE4D-Motion reconstructionFoot Slide: 4.03 -> 3.62Improved
use DINOv2 instead of EgoVideo image encoder (ablation)UniEgoMotion · EE4D-Motion reconstructionMPJPE: 0.132 -> 0.100Improved
use DINOv2 instead of EgoVideo image encoder (ablation)UniEgoMotion · EE4D-Motion forecastingFID: 0.060 -> 0.047Improved
use DINOv2 instead of CLIP image encoder (ablation)UniEgoMotion · EE4D-Motion generationFoot Slide: 3.57 -> 2.89Improved
use transformer decoder instead of transformer encoder (ablation)UniEgoMotion · EE4D-Motion reconstructionFID: 0.017 -> 0.027Hurt

Later papers that compared with this method

1 later accepted paper reports UniEgoMotion 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