Restoration Of Han Brick And Stone Relief From Single Rubbing Images

In this paper we propose a two-level approach for height map estimation from single rubbing images, aiming at restoring brick and stone relief (BSR) from their rubbing images in a visually plausible manner. This study is an important endeavor in promoting fragmented, stolen, or lost BSR and our work can be applied in a wide range of areas ranging from digital libraries, digital museums to embossment.In our approach, the base relief, referring to the low component of BSR, is estimated automatically with a partial differential equation (PDE) based mesh deformation scheme. The height map estimation for the base relief involves detection of object regions, determination of height constraints, PDE-based mesh deformation and conversion from 3D mesh to height map. Objects regions on rubbing images are first detected by the snake algorithm. A few vertices near the central area of the object region are selected and assigned with heights estimated by an erosion based contour map. These vertices together with object boundary vertices, boundary normals as well as the partial differential properties of the mesh are taken as constraints to deform the mesh by minimizing a least squares error functional. Finally we convert the 3D mesh for the base relief to a height map so that the final height map can be obtained by summing the height map of both base relief and high frequency detail.The high frequency detail is estimated directly from rubbing images automatically or optionally with minimal interactive processing. The final height map for a restored BSR is obtained by blending height maps of the base relief and high frequency detail.We demonstrate that our method can not only successfully restore several BSR maps from their rubbing images, but also restore some relief like surfaces from photographic images.