PerpetualWonder：长时程动作条件 4D 场景生成
PerpetualWonder: Long-horizon Action-conditioned 4D Scene Generation
把物理状态与视觉基元做双向绑定、并用多视角监督消解优化歧义，是让生成式细化能反过来修正底层物理的通用思路；做可交互场景生成或世界模型时，可直接借鉴这种闭环更新机制。
原文依据 a novel unified representation that creates a bidirectional link between the physical state and visual primitives
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 PerpetualWonder，一个混合生成式仿真器，能够从单张图像实现长时程、动作条件驱动的 4D 场景生成。现有工作在这一点上失败，原因在于其物理状态与视觉表征相互解耦，使得生成式细化无法更新底层物理以支持后续交互。PerpetualWonder 通过引入首个真正的闭环系统来解决这一问题。它采用一种新颖的统一表征，在物理状态与视觉基元之间建立双向链接，使生成式细化能够同时修正动力学与外观。它还引入一种鲁棒的更新机制，从多个视角收集监督以消解优化歧义。实验表明，从单张图像出发，PerpetualWonder 能够成功模拟由长时程动作驱动的复杂多步交互，并保持物理合理性与视觉一致性。
英文原文摘要 976 字符
We introduce PerpetualWonder, a hybrid generative simulator that enables long-horizon, action-conditioned 4D scene generation from a single image. Current works fail at this task because their physical state is decoupled from their visual representation, which prevents generative refinements to update the underlying physics for subsequent interactions. PerpetualWonder solves this by introducing the first true closed-loop system. It features a novel unified representation that creates a bidirectional link between the physical state and visual primitives, allowing generative refinements to correct both the dynamics and appearance. It also introduces a robust update mechanism that gathers supervision from multiple viewpoints to resolve optimization ambiguity. Experiments demonstrate that from a single image, PerpetualWonder can successfully simulate complex, multi-step interactions from long-horizon actions, maintaining physical plausibility and visual consistency.