Demiurge：通过自回归视频重渲染构建可导航的4D世界
Demiurge: Forging Navigable 4D Worlds via Autoregressive Video Rerendering
AI总结：
本文提出Demiurge，一种基于动态4D点云内存缓存的自回归视频重渲染流水线，解决现有方法跨轨迹一致性不足的问题，实现了连贯4D世界构建、大视差视频重渲染等能力，性能达SOTA。
摘要：
视频扩散技术的最新进展支持从单输入视频合成新视角视频，可应用于世界建模、具身智能和机器人仿真。然而现有方法独立处理相机轨迹，缺乏构建连贯、可导航4D世界所需的跨轨迹一致性。本文提出Demiurge，一种基于动态4D点云内存缓存的自回归视频重渲染流水线，通过四个组件提升跨轨迹一致性：（1）外观视频扩散模型，基于4D内存合成逼真的新视角视频；（2）内存一致的视频深度补全模型，对齐已知区域深度与缓存几何并补全缺失区域，缓解内存更新时的尺度歧义与不连续性；（3）内存感知双流扭曲，为新视角合成提供高保真视觉引导与遮挡线索；（4）几何感知视频精修，提升感知质量。大量实验表明该方法达到了SOTA性能，具备三项关键能力：在密集多视图轨迹上构建连贯时空格；在挑战性相机运动下（包括无输入视图重叠的180度旋转）实现大视差视频重渲染；生成几何保真的输出，可直接优化为高质量3D Gaussian Splatting表示且伪影极少。项目页面：this https URL。
英文摘要：
Recent advances in video diffusion enable novel-view video synthesis from a single input video, supporting world modeling, embodied intelligence, and robotic simulation. However, existing methods process camera trajectories independently, lacking the cross-trajectory consistency needed for coherent, navigable 4D worlds. We introduce Demiurge, an autoregressive video rerendering pipeline built on a dynamic 4D point-cloud memory cache. It promotes cross-trajectory consistency through four components: (1) an appearance video diffusion model that synthesizes photorealistic novel-view videos conditioned on the 4D memory; (2) a memory-consistent video depth completion model that aligns known-region depths with cached geometry and completes missing regions, mitigating scale ambiguity and discontinuities during memory updates; (3) memory-aware dual-stream warping that provides high-fidelity visual guidance and occlusion cues for novel-view synthesis; and (4) geometry-aware video refinement that enhances perceptual quality. Extensive experiments demonstrate state-of-the-art performance and three key capabilities: coherent spatiotemporal lattice construction over dense multi-view trajectories; large-parallax video rerendering under challenging camera motions, including 180-degree rotations with no input-view overlap; and geometry-faithful outputs that can be directly optimized into high-quality 3D Gaussian Splatting representations with minimal artifacts. Project page: this https URL.
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。
