V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties
This addresses the need for accurate and editable intrinsic property controls in video generation for applications in video editing and synthesis, representing a novel integration rather than an incremental improvement.
The paper tackles the problem of lacking a closed-loop framework for intrinsic-aware video editing by introducing V-RGBX, which unifies video inverse rendering, synthesis, and keyframe-based editing, resulting in temporally consistent, photorealistic videos that surpass prior methods in applications like object appearance editing and scene-level relighting.
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.