A Novel Stereoscopic View Generation Approach Based on Visual Attention Analysis

摘要

With the popularity of 3D films, the conversion of existing 2D videos to 3D videos has attracted a wide interest in 3D content production. In this paper, we present a novel stereoscopic view generation approach based on visual attention analysis. Depth map is firstly found by combining visual attention information with other structure related constrints in a united domain transform framework. Then the 2D image is converted to a stereoscopic one by DIBR (Depth Image Based Rendering). Experiments show that the proposed approach can yield visually satisfactory results.