A novel technique for multi-scale smoothing of a free-form 3-D surface is presented. Diffusion of the surface is achieved through convolutions of local parametrisations of the surface with a 2-D Gaussian filter. Our method for local parametrisation makes use of semigeodesic coordinates as a natural and efficient way of sampling the local surface shape. The smoothing eliminates the surface noise together with high curvature regions such as sharp edges, therefore, sharp corners become rounded as the object is smoothed iteratively. During smoothing some surfaces can become very thin locally. Application of decimation followed by refinement removes very small/ thin triangles and segments those surfaces into parts which are then smoothed separately. Furthermore, surfaces with holes and surfaces that are not simply connected do not pose any problems. Our method is also more efficient than those techniques since 2-D rather than 3-D convolutions are employed. It is also argued that the pro...