WorldWarp：基于异步视频扩散的三维几何传播

WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion

December 22, 2025

作者: Hanyang Kong, Xingyi Yang, Xiaoxu Zheng, Xinchao Wang

cs.AI

摘要

生成具有长距离几何一致性的视频面临一个根本性困境：几何一致性要求严格遵循像素空间的三维几何规律，而最先进的生成模型却在相机条件化的潜空间中运行最为高效。这种脱节导致现有方法在处理遮挡区域和复杂相机轨迹时表现不佳。为弥合这一差距，我们提出WorldWarp框架，该框架将三维结构锚点与二维生成优化器相结合。为实现几何基础，WorldWarp通过高斯溅射（3DGS）技术维护在线三维几何缓存。通过显式地将历史内容变换到新视角，该缓存充当结构支架，确保每一帧新画面都遵循先前的几何关系。然而静态变换会因遮挡不可避免地产生空洞和伪影。我们采用专为"填充-修正"目标设计的时空扩散（ST-Diff）模型解决此问题。核心创新在于时空动态噪声调度机制：空白区域接受全噪声以触发生成，而变换区域则接受部分噪声以实现优化。通过逐帧动态更新三维缓存，WorldWarp在视频片段间保持一致性，最终以三维逻辑指导结构、扩散逻辑完善纹理的方式实现业界顶尖的生成质量。项目页面：https://hyokong.github.io/worldwarp-page/。

English

Generating long-range, geometrically consistent video presents a fundamental dilemma: while consistency demands strict adherence to 3D geometry in pixel space, state-of-the-art generative models operate most effectively in a camera-conditioned latent space. This disconnect causes current methods to struggle with occluded areas and complex camera trajectories. To bridge this gap, we propose WorldWarp, a framework that couples a 3D structural anchor with a 2D generative refiner. To establish geometric grounding, WorldWarp maintains an online 3D geometric cache built via Gaussian Splatting (3DGS). By explicitly warping historical content into novel views, this cache acts as a structural scaffold, ensuring each new frame respects prior geometry. However, static warping inevitably leaves holes and artifacts due to occlusions. We address this using a Spatio-Temporal Diffusion (ST-Diff) model designed for a "fill-and-revise" objective. Our key innovation is a spatio-temporal varying noise schedule: blank regions receive full noise to trigger generation, while warped regions receive partial noise to enable refinement. By dynamically updating the 3D cache at every step, WorldWarp maintains consistency across video chunks. Consequently, it achieves state-of-the-art fidelity by ensuring that 3D logic guides structure while diffusion logic perfects texture. Project page: https://hyokong.github.io/worldwarp-page/{https://hyokong.github.io/worldwarp-page/}.