A Nonlocal Filter-Based Hybrid Strategy for Depth Map Enhancement

This paper presents a novel hybrid strategy for depth map enhancement. Given a low resolution and noisy depth map, we improve its spatial resolution and quality with a registered high resolution color image. The unreliable pixels are removed firstly based on the local structure of center pixel. Then the initial depth map is mapped to color image´s coordinate. And the holes created by up sampling and unreliable invalidation are filled by nonlocal filter-based method. Different from the previous local filter-based methods, nonlocal filter does not require the optimal support window and more natural pixel similarity measure metric is given. By quantitative and qualitative experiments on publicly available test sequences, we demonstrate the effectiveness and efficiency of our proposed method on the depth enhancement task, compared with the existing methods.