Abstract: For the foreground and background segmentation in three-dimensional video inpainting,the inaccuracy of the foreground extraction is easily to affect the quality of the repaired image.In order to solve this problem,this paper proposes a new three-dimensional video inpainting algorithm based on the combination of gradient fusion and cluster.Firstly,the proposed algorithm combines watershed algorithm with marker for image segmentation,making full use of the structural information of the depth image.Then in order to enhance the ability of distinguishing the foreground objects,K-means clustering is introduced to mark them in the gradient image.The experimental results show that the improved algorithm overcomes the defect of original watershed algorithm in image segmentation,which is likely to occur the over-segmentation phenomenon,and it also can completely extract the texture information of the foreground object,making the repaired image have a better visual effect,and the peak signal-to-noise ratio(PSNR)is increased by 1 to 3 dB,compared to the other algorithm.