Multi-view video plus depth (MVD) is the main format of three-dimension (3D) v ideo.Under the framework 3D high efficiency video coding (HEVC) the computationa l complexity of depth video intra coding is huge.Moreover,the inaccuracy of esti mated depth video will bring about the growth of texture in the flat region,which significa ntly increases the computational complexity of intra coding.To tackle these problems,a preprocessin g based depth video fast intra coding algorithm is proposed in this paper.Firstly,in order to remove the texture cau sed by inaccurate depth video,a smoothing method is applied before encoding.Then,the largest partition depth ( LPD) of largest coding unit (LCU) in depth video can be predicted by backpropagation neural network (BPNN).Lastly, the process of LCU partitioning can be terminated in advance according to edge information of depth video and the LPD of LCU in corresponding color video.Experimental results demonstrate that the algor ithm can save the time of depth video coding by 50.63% on average with negligible quality degradation of virtual view.