AI Paper Atlas

Research map / Video / Video generation

PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groups

Sakuya Ota, Qing Yu, Kent Fujiwara, Satoshi Ikehata, Ikuro Sato

ICCV 2025 · Video › Video generation · approach: Text-to-motion diffusion · 6 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 PINO overlap-penalty noise optimizationInterGen · Two-person interaction (InterHuman, 300 samples)Overlap: 0.119 -> 0.000Improved
add PINO noise optimizationInterGen · Two-person interaction (InterHuman, 300 samples)Penetration volume (cm^3): 3112.72 -> 275.65Improved
add PINO noise optimizationInterGen · Two-person interaction (InterHuman, 300 samples)FID: 13.278 -> 13.163Improved
add PINO to sequential multi-person generationInterGen · Five-person generation, pair (1,5)Overlap: 0.977 -> 0.069Improved
add PINO to sequential multi-person generationInterGen · Five-person generation, pair (1,5)Foot skate: 0.124 -> 0.142Hurt
add root-position penalty (ablation)InterGen · Penalty ablation (two agents, 24 sequences per configuration)Position error rate: 1.0 -> 0.0Improved
add root-position penalty (ablation)InterGen · Penalty ablation (two agents, 24 sequences per configuration)Region violation rate: 0.500 -> 0.917Hurt
add overlap penalty (ablation)InterGen + root penalty · Penalty ablation (two agents, 24 sequences per configuration)Overlap rate: 0.333 -> 0.0Improved
add movement region penalty (ablation)InterGen + root + overlap · Penalty ablation (two agents, 24 sequences per configuration)Region violation rate: 0.958 -> 0.043Improved
add orientation penalty (ablation)InterGen + root + overlap + region · Penalty ablation (two agents, 24 sequences per configuration)Orientation error rate: 1.0 -> 0.208Improved
add PINO to motion extensionInterGen (inpainting) · Motion extension (two-person, non-semantic)Overlap: 0.672 -> 0.031Improved
add PINO to motion extensionInterGen · Motion extension (two-person, cropped to GT length)FID: 20.390 -> 18.930Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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