Reproduce “Event-Driven Storytelling with Multiple Lifelike Humans in a 3D Scene” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Donggeun Lim, Jinseok Bae, Inwoo Hwang, Seungmin Lee, Hwanhee Lee, Young Min Kim
Event-Driven Storytelling plans multi-character behavior in furnished 3D scenes by organizing actions into events and translating them into grounded motion instructions. A parser locates characters in semantic areas around objects, while a motion module plans paths and actions. On the OA/RC/SS benchmark, GPT-4o achieves 0.90 success versus 0.82 without events; this ablation supports the combined design, not a causal effect alone.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.