AI Paper Atlas

Research map / 3D vision / Human pose estimation

Scene-aware Human Motion Forecasting via Mutual Distance Prediction

Chaoyue Xing, Wei Mao, Miaomiao Liu

ECCV 2024 · 3D vision › Human pose estimation · approach: Human motion prediction · 9 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 mutual distance prediction to scene-aware forecasting (ablation)Scene-only forecasting model · HUMANISE seen scenesPath error (mm) mean: 52.6 -> 45.6Improved
add scene input to motion-only model (ablation)Motion only · HUMANISE seen scenesPath error (mm) mean: 57.0 -> 52.6Improved
add per-vertex signed distance (ablation)Mutual distance model · HUMANISE seen scenesPath error (mm) mean: 46.2 -> 45.6Improved
add per-basis point distance (ablation)Mutual distance model · HUMANISE seen scenesPath error (mm) mean: 50.6 -> 45.6Improved
use SDF volume scene input instead of point cloud (ablation)Mutual distance model · HUMANISE seen scenesPath error (mm) mean: 49.3 -> 45.6Improved
use SDF volume scene input instead of occupancy volume (ablation)Mutual distance model · HUMANISE seen scenesPath error (mm) mean: 55.3 -> 45.6Improved
use per-basis point distance instead of BPS encoding (ablation)Mutual distance model · HUMANISE seen scenesPath error (mm) mean: 53.9 -> 45.6Improved
use stage-wise training instead of end-to-end from scratch (ablation)Mutual distance model · HUMANISE seen scenesPath error (mm) mean: 51.5 -> 45.6Improved
replace predicted contact map with predicted mutual distance (ground-truth input version)STAG / ContAware · GTA-IMPath error (mm) mean: 40.0 -> 22.4Improved
mutual distance vs contact map on pose error with GT inputSTAG w/GT · HUMANISE seen scenesPose error 1.0s: 117.6 vs 122.0Mixed

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