V-RGBX：具有精确内在属性控制的视频编辑
V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties
AI总结：
V-RGBX通过端到端框架实现基于内在属性的视频编辑，支持直观且物理合理的视频修改，适用于物体外观和场景重照明等应用。
摘要：
大规模视频生成模型在建模真实世界场景中的逼真外观和光照交互方面展现了显著潜力。然而，一个能够联合理解内在场景属性（例如，反光率、法线、材质和辐照度），利用这些属性进行视频合成，并支持可编辑内在表示的闭环框架仍未被探索。我们提出了V-RGBX，这是首个针对内在感知视频编辑的端到端框架。V-RGBX统一了三个关键能力：（1）将视频反向渲染到内在通道；（2）从这些内在表示中生成逼真视频；（3）基于关键帧的视频编辑，条件于内在通道。V-RGBX的核心是一种交错的条件机制，它通过用户选择的关键帧实现直观、物理基础的视频编辑，支持对任何内在模态的灵活操控。广泛的定性和定量结果表明，V-RGBX在生成时间一致、逼真视频的同时，能够以物理合理的方式在序列中传播关键帧编辑。我们展示了其在多样化应用中的有效性，包括物体外观编辑和场景级重照明，超越了先前方法的性能。
英文摘要：
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.
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。
