A new common-hole filling algorithm for virtual view synthesis with a probability mask

In this paper, a new common-hole filling algorithm with a probability mask for a virtual view synthesis is proposed. In the proposed algorithm, we try to combine strong points of both the spiral weighted average algorithm and the gradient searching algorithm. The spiral weighted average algorithm keeps the boundary of each object well by using depth information and the gradient searching algorithm is able to preserve details. We also try to reduce the flickering defect existing around the filled common-hole region by using a probability mask. The experimental results show that the proposed algorithm performs much better than conventional algorithms.