AI Paper Atlas

Research map / 3D vision / 3D generation

HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes

Zan Wang, Yixin Chen, Tengyu Liu, Yixin Zhu, Wei Liang, Siyuan Huang

NeurIPS 2022 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 22 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 target-object grounding loss (ablation)HUMANISE model · HUMANISE, all actionsgoal dist.: 1.008 -> 1.383Improved
add action classification loss (ablation)HUMANISE model · HUMANISE, all actionsaction score: 2.29$\pm$1.43 -> 3.59$\pm$1.38Improved
add both object-grounding and action-classification auxiliary losses (ablation)HUMANISE model · HUMANISE, all actionsquality score: 1.97$\pm$0.98 -> 2.57$\pm$1.20Improved
fuse scene and language features using self-attention rather than direct concatenation (ablation)HUMANISE model · HUMANISE, walkgoal dist.: 1.500 -> 1.370Improved
use Point Transformer instead of PointNet++ for scene encoding (ablation)HUMANISE model · HUMANISE, walkgoal dist.: 1.444 -> 1.370Improved
use the full grounding-loss weight rather than reducing alpha_o (ablation)HUMANISE model · HUMANISE, lie downgoal dist.: 0.444 -> 0.196; 0.306 -> 0.196; 0.211 -> 0.196Mixed
train using the full lie-down dataset rather than 50% of it (ablation)HUMANISE model · HUMANISE, lie downgoal dist.: 0.177 -> 0.196Hurt
train using the full lie-down dataset rather than 10% of it (ablation)HUMANISE model · HUMANISE, lie downMPJPE: 248.82 -> 136.87Improved
pre-train the motion synthesis model on HUMANISE before fine-tuning on PROXhuman motion synthesis model · PROX test splittranslation: 7.65 -> 6.54Improved
provide ground-truth target position instead of relying on predicted language groundingHUMANISE model · HUMANISE, all actionsgoal dist.: 1.008 -> 0.207Improved
provide ground-truth action instead of parsing action from the language descriptionHUMANISE model · HUMANISE, all actionsgoal dist.: 1.008 -> 1.406Mixed

Later papers that compared with this method

3 later accepted papers report Humanise as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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