Image-based surface detail transfer - Computer Graphics and Applications, IEEE

geometric details is desirable in many real-world applications. We might want to know, for example, how a wall would look after adding some geometrical bumps, or how a person would look after adding wrinkles on his or her face. Direct methods for adding geometric details to an object require modeling the object and the surface details. It’s usually not a trivial task to build a 3D model for a real object. It’s also tedious and labor intensive to model and create surface details with existing geometric modeling tools. Bump mapping has acted as an alternative to adding geometrical details to an otherwise smooth object. But constructing visually interesting bump maps requires practice and artistic skills. Computer vision techniques have helped for modeling real-world objects and their surface details. Techniques include the use of laser scanner, stereo algorithms, shape from lighting variation, shape from shading, and so on. However, some of these techniques require specialized equipment. Many other techniques require at least two images of each object, and capturing highresolution geometrical details robustly can be difficult. Although the shape-from-shading technique only requires a single image, this approach usually requires knowledge of the lighting condition and reflectance functions of the surface material. Three-dimensional recognition and reconstruction from a single image have used linear classes of objects. But this reconstruction technique doesn’t generate accurate geometric details. In our approach, for cases where we only want to transfer geometrical details from one object to another, we might not need to explicitly compute 3D structures. In particular, our novel technique captures the geometrical details of an object from a single image in a way that is independent of the object’s reflectance property. We can then transfer geometrical details to another surface, producing the appearance of a new surface with added geometrical details while preserving the object’s reflectance property. Our method’s advantages are that it’s simple to implement, requires only a single image for each object, and produces effective results. An earlier version of this article appeared in the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. In this revised version, we show that this technique is suitable as a fast and effective touch-up tool for photo editing. In particular, it can remove wrinkles and color spots on face images.