Image-based Animation of Clothes

Abstract

We propose a pose-dependent image-based rendering approach for the visualization of clothes with very high rendering quality. Our representation combines body-pose-dependent geometry and appearance. A geometric model accounts for low-resolution shape adaptation, e.g. animation and view interpolation, while small details as well as complex shading/reflection properties are accounted for through numerous images. Information on shading, texture distortion and silhouette at fine wrinkles are extracted from the images to allow later texture replacement. The image-based representations are estimated in advance from real samples of clothes captured in an offline process, thus shifting computational complexity into the training phase. For rendering, pose dependent geometry and appearance are interpolated and merged from the stored representations.