PROJECT TITLE :

Depth Sensation Enhancement for Multiple Virtual View Rendering

ABSTRACT:

Depth info is an indispensable element thorough image-based rendering (DIBR) for 3-dimensional (three-D) show. In this paper, we have a tendency to propose a completely unique depth sensation enhancement method to address the problems in multiple virtual read rendering. 1st, because the depth sensation is decreased when rendering intermediate multiple virtual views, the essential principle of depth sensation enhancement springs in step with the amount of rendering views. Second, with the rise of the scene complexity, it is difficult to make sure the depth sensation of all neighboring objects. The saliency analysis is adopted to offer most well-liked guarantee to the depth sensation between the salient object and its neighbors. Then, the depth sensation enhancement for multiple virtual read rendering is performed based on a defined energy operate engineered by the number of rendering views and also the saliency analysis. Finally, considering the temporal consistency between adjacent frames, the depth sensation enhancement is extended to video applications with a newly designed energy operate with energy term of temporal consistency preservation. Experimental results on a public database demonstrate that the proposed method can acquire promising performance in depth sensation.