Large-scale video generation models have shown remarkable potential in modeling photorealistic appearance and lighting interactions in real-world scenes. However, a closed-loop framework that jointly understands intrinsic scene properties (e.g., albedo, normal, material, and irradiance), leverages them for video synthesis, and supports editable intrinsic representations remains unexplored. We present V-RGBX, the first end-to-end framework for intrinsic-aware video editing. V-RGBX unifies three key capabilities: (1) video inverse rendering into intrinsic channels, (2) photorealistic video synthesis from these intrinsic representations, and (3) keyframe-based video editing conditioned on intrinsic channels. At the core of V-RGBX is an interleaved conditioning mechanism that enables intuitive, physically grounded video editing through user-selected keyframes, supporting flexible manipulation of any intrinsic modality. Extensive qualitative and quantitative results show that V-RGBX produces temporally consistent, photorealistic videos while propagating keyframe edits across sequences in a physically plausible manner. We demonstrate its effectiveness in diverse applications, including object appearance editing and scene-level relighting, surpassing the performance of prior methods.

翻译：大规模视频生成模型在模拟真实世界场景中的逼真外观与光照交互方面展现出显著潜力。然而，一个能够联合理解场景固有属性（如反照率、法线、材质与辐照度）、利用这些属性进行视频合成并支持可编辑固有表征的闭环框架仍未被探索。本文提出V-RGBX，首个面向固有属性感知视频编辑的端到端框架。V-RGBX统一了三个核心功能：（1）将视频逆向渲染为固有通道；（2）基于这些固有表征进行逼真视频合成；（3）以固有通道为条件的关键帧驱动视频编辑。V-RGBX的核心是一种交错条件机制，通过用户选择的关键帧实现直观且基于物理原理的视频编辑，支持对任意固有模态的灵活操控。大量定性与定量结果表明，V-RGBX能生成时序一致、逼真的视频，并以物理合理的方式将关键帧编辑效果传播至整个序列。我们通过物体外观编辑与场景级重照明等多样化应用验证了其有效性，其性能超越现有方法。