EnvSocial-Diff: 一种基于扩散的群体模拟模型,包含环境条件和个体-群体交互
EnvSocial-Diff: A Diffusion-Based Crowd Simulation Model with Environmental Conditioning and Individual-Group Interaction
AI总结:
本文提出EnvSocial-Diff模型,结合社会物理和环境条件,通过环境编码模块和个体-群体交互模块提升群体模拟的现实性,实验表明其优于现有方法。
摘要:
建模真实的行人轨迹需要考虑社会互动和环境上下文,但大多数现有方法侧重于社会动态。我们提出了EnvSocial-Diff:一种基于扩散的群体模拟模型,受社会物理启发,并增强环境条件和个体-群体交互。我们的结构化环境条件模块显式编码障碍物、感兴趣物体和光照水平,提供可解释信号,捕捉场景约束和吸引点。同时,个体-群体交互模块通过图结构设计,超越个体层面建模,通过捕捉细粒度人际关系和群体层面的从众行为。实验表明EnvSocial-Diff在多个基准数据集上优于最新方法,凸显了显式环境条件和多层级社会交互对真实群体模拟的重要性。代码见:https://github.com/zqyq/EnvSocial-Diff.
英文摘要:
Modeling realistic pedestrian trajectories requires accounting for both social interactions and environmental context, yet most existing approaches largely emphasize social dynamics. We propose \textbf{EnvSocial-Diff}: a diffusion-based crowd simulation model informed by social physics and augmented with environmental conditioning and individual--group interaction. Our structured environmental conditioning module explicitly encodes obstacles, objects of interest, and lighting levels, providing interpretable signals that capture scene constraints and attractors. In parallel, the individual--group interaction module goes beyond individual-level modeling by capturing both fine-grained interpersonal relations and group-level conformity through a graph-based design. Experiments on multiple benchmark datasets demonstrate that EnvSocial-Diff outperforms the latest state-of-the-art methods, underscoring the importance of explicit environmental conditioning and multi-level social interaction for realistic crowd simulation. Code is here: https://github.com/zqyq/EnvSocial-Diff.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。