This paper describes a depth-based inpainting algorithm which efficiently handles disocclusion occurring on virtual viewpoint rendering. A single reference view and a set of depth maps are used in the proposed approach. The method not only deals with small disocclusion filling related to small camera baseline, but also manages to fill in larger disocclusions in distant synthesized views. This relies on a coherent tensor-based color and geometry structure propagation. The depth is used to drive the filling order, while enforcing the structure diffusion from similar candidate-patches. By acting on patch prioritization, selection and combination, the completion of distant synthesized views allows a consistent and realistic rendering of virtual viewpoints.

In this paper, we propose a novel inpainting algorithm combining the advantages of PDE-based schemes and examplar-based approaches. The proposed algorithm relies on the use of structure tensors to define the filling order priority and template matching. The structure tensors are computed in a hierarchic manner whereas the template matching is based on a K-nearest neighbor algorithm. The value K is adaptively set in function of the local texture information. Compared to two state of the art approaches, the proposed method provides more coherent results.

Abstract-The multi-view plus depth video (MVD) format has recently been introduced for 3DTV and free-viewpoint video (FVV) scene rendering. Given one view (or several views) with its depth information, depth image-based rendering techniques have the ability to generate intermediate views. The MVD format however generates large volumes of data which need to be compressed for storage and transmission. This paper describes a new depth map encoding algorithm which aims at exploiting the intrinsic depth maps properties. Depth images indeed represent the scene surface and are characterized by areas of smoothly varying grey levels separated by sharp edges at the position of object boundaries. Preserving these characteristics is important to enable high quality view rendering at the receiver side. The proposed algorithm proceeds in three steps: the edges at object boundaries are first detected using a Sobel operator. The positions of the edges are encoded using the JBIG algorithm.The luminance values of the pixels along the edges are then encoded using an optimized path encoder. The decoder runs a fast diffusion-based inpainting algorithm which fills in the unknown pixels within the objects by starting from their boundaries. The performance of the algorithm is assessed against JPEG-2000 and HEVC, both in terms of PSNR of the depth maps versus rate as well as in terms of PSNR of the synthesized virtual views.