Re-texturing by Intrinsic Video

Abstract

In this paper, we present a novel re-texturing approach using intrinsic video. Our approach begins with indicating the regions of interests by contour-aware layer segmentation. Then, the intrinsic video (including reflectance and illumination components) within the segmented region is recovered by our weighted energy optimization. After that, we compute the normals for the re-textured region, and the texture coordinates in key frames through our newly developed optimization approach. At the same time, the texture coordinates in non-key frames are optimized by our proposed energy function. Finally, when the target sample texture is specified, the re-textured video is created by multiplying the re-textured reflectance component by the original illumination component within the replaced region. As demonstrated in our experimental results, our method can produce high quality video re-texturing results with preserving the lighting and shading effect of the original video.