AI Paper Atlas

Research map / 3D vision / 3D generation

IntentMotion: Learning Intent-Aware Human Motion from Language in 3D Scenes

Wenfeng Song, Shi Zheng, Xinyu Zhang, Xingliang Jin, Aimin Hao, Fei Hou, Xia Hou, Shuai Li

AAAI 2026 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 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 contact conditioning (IGCF) (ablation)IntentMotion · HUMANISEFID: 0.233 -> 0.163Improved
add hierarchical attention instead of MLP for contact fusion (ablation)IGCF · HUMANISEFID: 0.203 -> 0.163Improved
increase alignment depth from 4 to 6 self-attention layers (ablation)IGCF · HUMANISEFID: 0.163 -> 0.216Hurt
reduce alignment depth from 4 to 2 (ablation)IGCF · HUMANISEFID: 0.163 -> 0.156No clear effect
add coarse and fine guidance to Adapt-Dec (ablation)IADM · HUMANISEFID: 0.200 -> 0.163Improved
use Adapt-Dec instead of U-Net denoiser (ablation)IADM · HUMANISEFID: 0.994 -> 0.163Improved
use Adapt-Dec instead of DiT denoiser (ablation)IADM · HUMANISEFID: 0.247 -> 0.163Improved
add IGCF module to Adapt-Dec baseline (ablation)Cen et al.* · LINGOpenetration rate: 0.261 -> 0.119Improved
add target object groundingIntentMotion · HUMANISEcontact: 95.63 -> 95.30 contact; FID 0.255 -> 0.163Mixed

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