AI Paper Atlas

Research map / 3D vision / 3D generation

Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scene

Donggeun Lim, Jinseok Bae, Inwoo Hwang, Seungmin Lee, Hwanhee Lee, Young Min Kim

ICCV 2025 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 2 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 event-driven planning (narrator and event parser) (ablation)GPT-4o planner · Multi-agent planning benchmarksuccess rate: 0.82 -> 0.9Improved
add event-driven planning (ablation)GPT-4o mini planner · Multi-agent planning benchmarksuccess rate: 0.6 -> 0.74Improved
add event-driven planning (ablation)Llama-3.1-8B planner · Multi-agent planning benchmarksuccess rate: 0.31 -> 0.35Improved
add event-driven planning, scene-state tag (ablation)GPT-4o planner · Multi-agent planning benchmark (SS)success rate: 0.77 -> 0.92Improved
add event-driven planning (ablation)DeepSeek-V3 planner · Multi-agent planning benchmarksuccess rate: 0.82 -> 0.83No clear effect
use context-centric scene description instead of object list (ablation)GPT-4o planner · Multi-agent planning benchmarksuccess rate: 0.51 -> 0.9Improved
use context-centric scene description instead of scene graph (ablation)GPT-4o mini planner · Multi-agent planning benchmarksuccess rate: 0.49 -> 0.74Improved
use context-centric scene description instead of scene graph (ablation)Llama-3.1-70B planner · Multi-agent planning benchmarksuccess rate: 0.72 -> 0.72No clear effect
use area-conditioned position sampling instead of direct coordinates (ablation)GPT-4o planner · PI benchmarksuccess rate: 0.46 -> 0.94Improved
use area-conditioned position sampling instead of direct coordinates (ablation)Qwen2.5-72B planner · PI benchmarksuccess rate: 0.14 -> 1.0Improved
use area-conditioned position sampling instead of direct coordinates (ablation)Llama-3.1-8B planner · PI benchmarksuccess rate: 0.14 -> 0.86Improved
replace text scene description with vision-generated description (ablation)GPT-4o planner · Multi-agent planning benchmarksuccess rate: 0.9 -> 0.68Hurt

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