The estimation of a depth map using spatial continuity and edges

Abstract

This paper deals with creating depth maps from two images. The initial map is created using the sum of the absolute differences of the each image point's neighborhood. Many discontinuities are in this map. Therefore, we have to use some approach for its improvement. The proposed method utilizes a combination of a few approaches. The first approach is based on the assumption of continuity of the depth map in rows and utilizing information about edges in images. We designed rules for filling zero areas in the initial depth map. The second step uses disparity of significant points found in zero areas. The significant points are found by the algorithm Speeded Up Robust Features (SURF). The applicability of the proposed method is demonstrated on a few images from Middlebury Stereo Datasets. In the future, we will execute subjective tests for examining the influence of the depth map to the evaluation of the spatial effect. The proposed methods will be used as tool for depth maps generation with various quality.

Holographic 3D Display Using Depth Maps Generated by 2D-to-3D Rendering Approach

“…However, a 2D-to-3D rendering approach that uses only one of these features may not be widely applicable. Therefore, 2D-to-3D rendering approaches that use mixed features have been employed [27][28][29]. The CGDMs calculated by the mixed-features-based method are more stable than that by single-feature-based method.…”