Simultaneous 3D Shape and Multi-view Silhouette Estimation with Error Detection and Correction by Spatiotemporal Constraints

点击翻译按钮获取中文摘要

This research proposed a new algorithm utilizing spatiotemporal multiple-view consistency among the 3D shape and its silhouettes of a single object. The key contribution is the computational model to make the estimation robust against uncontrolled real world. In addition, this research proposed a new novel-view synthesis algorithm which well suits for such real-world environment.