Adaptive edge-oriented depth image smoothing approach for depth image based rendering

A depth image based rendering (DIBR) is the process which uses one 2D color image and its associated depth image to render virtual view images. A problem in DIBR is how to reduce the number of holes occurring on the generated virtual view images. To reduce the holes occurrence, the depth image is pre-processed by smoothing filter before image warping. However, smoothing the whole depth image may introduce some geometric distortions on the generated virtual images and increase the computational time. In this paper, an adaptive edge-oriented smoothing process is proposed to solve the problem. The proposed method adopts an edge dependent depth filter to predict the holes region and then the horizontal smoothing filter is first employed on the predicted holes regions. If hole regions are with vertical edges, the depth image is further pre-processed by asymmetric smoothing filter. The experimental results show that the proposed method can reduce the geometric distortions on the virtual view and preserve the depth quality.