利用拓片恢复汉画像的浮雕效果

Restoration of Han Dynasty Brick and Stone Relief from Rubbing Images

针对利用宣纸对汉画像进行拓印得到的拓片缺乏三维浮雕效果的问题,提出一种从汉画像拓片图像中恢复其浮雕表面的方法.将汉画像浮雕表面分成低频和高频分量2个部分:低频分量估计包括物体边缘检测,采用直方图估计物体边缘模糊度来确定浮雕起伏过度区域,用先验函数定义浮雕高度起伏,并用其插值估计物体区域内部的浮雕高度变化;高频细节则直接从拓片图像中加入少量交互进行估计;最终的汉画像三维浮雕高度由上述2个部分加权叠加得到.最后通过实例验证了文中方法的有效性.

We present a system framework for restoration of Han dynasty brick and stone relief （BSR） height from their rubbing images. In our approach we divide BSR into the base relief of low frequency component and the high frequency details. The base relief estimation involves detection of object regions on rubbing images, determination of transitive region for raised slop inside object regions with a histogram based edge sharpness estimation method, definition of raised slope with empirical functions and estimation of height variations inside object regions by a simple interpolation scheme. The estimation of high frequency details involves inverting pixel values of rubbing images and minimal interactive processing. The final height map for restored BSR is obtained by blending height maps of the low frequency component and high frequency details. We tested our method by successfully restoring some BSR.