Model-based video coding has been adopted as a core experiment in ISO MPEG-
4 standard. The clip-and-paste technique for putting video objects in line
is an important tool to reduce the transmission rate. To assist the clip-an
d-pasting method fitting into the 2-D model, we propose several smoothing a
lgorithms for improving the quality of the reconstructed images. In this pa
per, the proposed smoothing algorithms can adjust deformations of zoom, til
t, and rotation object images. Luminance smoothing algorithm is also applie
d to compensate the light source variations. Simulation results show that t
he smoothing methods help to improve clip-and-paste images to achieve a sat
isfactory quality in visual perceptions.