感知式 3D 仿真与物理世界建模
Perceptual 3D Simulation With Physical World Modeling
把感知建模为多模态场景变量的概率推断，并用部分 3D 变换信号作为条件、用持久场景记忆做在线一致性更新，这一「学习式世界模型 + 显式几何条件」的组合可直接迁移到新视角合成与动态场景预测任务中，作为对纯数据驱动生成模型的归纳偏置补充。
原文依据 a physical world modeling system that simulates future scene states under both partial observations and incomplete 3D transformation signals
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从图像出发预测场景在期望的 3D 变换之后将如何演化，是视觉、图形学与机器人领域的核心目标。然而，与能够完整获取 3D 几何与动力学的理想仿真器不同，真实世界系统必须依赖本质上片面且不完整的感知输入与局部动作。在本工作中，我们提出 P3Sim，一个物理世界建模系统，可在部分观测与不完整 3D 变换信号下仿真未来的场景状态。P3Sim 由三个相互作用的组件构成：学习得到的物理世界模型、几何条件模块以及持久场景记忆。世界模型将感知解释为对多模态场景变量的概率推断，给出以任意其他变量组合为条件时任意场景变量分布的预测。几何条件模块提供部分 3D 变换信号，用于在推理时对世界模型施加条件。持久场景记忆随时间整合预测结果，从而在不确定性下实现在线更新与一致性。通过将学习式推断与显式几何结构相结合，P3Sim 在数据驱动的灵活性与内建的归纳偏置之间取得平衡。这一设计产生了一个灵活的感知式仿真器，可泛化到多种 3D 变换任务，例如新视角合成、物体操作与动态场景预测，从而朝着通用 3D 场景理解与变换迈进。
英文原文摘要 1491 字符
Predicting how a scene will evolve after a desired 3D transformation from images is a central goal in vision, graphics, and robotics. Yet unlike ideal simulators with full access to 3D geometry and dynamics, real world systems must rely on perceptual inputs and local actions that are inherently partial and incomplete. In this work, we present P3Sim, a physical world modeling system that simulates future scene states under both partial observations and incomplete 3D transformation signals. P3Sim is composed of three interacting components: a learned physical world model, a geometric conditioning module, and a persistent scene memory. The world model interprets perception as probabilistic inference over multimodal scene variables, providing predictions of the distributions of any scene variable conditioned on any combination of others. The geometric conditioning module provides a partial 3D transform signal for conditioning the world model at inference time. The persistent scene memory integrates predictions over time, enabling online updates and consistency under uncertainty. By combining learned inference with explicit geometric structure, P3Sim balances data-driven flexibility with built-in inductive bias. This design yields a flexible perceptual simulator that generalizes across diverse 3D transformation tasks, such as novel view synthesis, object manipulation, and dynamic scene prediction, advancing toward general purpose 3D scene understanding and transformation.