Interactive Intrinsic Video Editing

Figure 1: A video sequence (a) is interactively decomposed into temporally consistent components for reflectance (b, top) and illumination (b, bottom). Now, editing the textures in the reflectance image does not affect the illumination (c): changes to the brick walls, the roof tiles, and the pathway leading up to the building all maintain the complex illumination of the light through the trees. We encourage readers to zoom into this figure to see the details in our results, and refer them to the accompanying video to see the temporally consistent nature of our decomposition. Separating a photograph into its reflectance and illumination intrinsic images is a fundamentally ambiguous problem, and state-of-the-art algorithms combine sophisticated reflectance and illumination priors with user annotations to create plausible results. However, these algorithms cannot be easily extended to videos for two reasons: first, naı̈vely applying algorithms designed for single images to videos produce results that are temporally incoherent; second, effectively specifying user annotations for a video requires interactive feed-back, and current approaches are orders of magnitudes too slow to support this. We introduce a fast and temporally consistent al