Automatic stereoscopic video generation based on virtual view synthesis

Abstract Automatically synthesizing 3D content from a causal monocular video has become an important problem. Previous works either use no geometry information, or rely on precise 3D geometry information. Therefore, they cannot obtain reasonable results if the 3D structure in the scene is complex, or noisy 3D geometry information is estimated from monocular videos. In this paper, we present an automatic and robust framework to synthesize stereoscopic videos from casual 2D monocular videos. First, 3D geometry information (e.g., camera parameters, depth map) are extracted from the 2D input video. Then a Bayesian-based View Synthesis (BVS) approach is proposed to render high-quality new virtual views for stereoscopic video to deal with noisy 3D geometry information. Extensive experiments on various videos demonstrate that BVS can synthesize more accurate views than other methods, and our proposed framework also outperforms state-of-the-art automatic 2D-to-3D conversion approaches.