Improved Depth Image-Based Rendering Using an Adaptive Compensation Method on an Autostereoscopic 3-D Display for a Kinect Sensor

Abstract

Depth image-based rendering (DIBR) is a 2-D-3-D view conversion technology in a space domain that corresponds to depth map. DIBR system requires only a single color image and an associated depth map to generate synthesized autostereoscopic 3-D views, but the quality of the result is depreciated due to the disoccluded areas in the depth map. Because of this problem, an improved DIBR method that uses a depth map adaptive compensation method is proposed. Using a fast parallax lookup table, the position of holes is allocated and depth map is split into blocks for statistical analysis and classification in order to estimate the quantity of holes. The result of the classification is used for adaptive multimode filtering to optimize the depth map. The experimental results show that the proposed method not only enhances the quality of depth map by compensating for the bigger and smaller areas of holes referring to analysis results, and by determining the filling method using the type of holes, but also reduces the number of holes that retain better depth map and reduces computation time.