Title: Multilayer semitransparent-edge processing for depth-image-based rendering
Abstract: Owing to the movie industry's wide use of 2D-to-3D conversion techniques, the problem of synthesizing stereoscopic views using depth-image-based rendering (DIBR) is extremely important. A major challenge for DIBR is processing semitransparent edges near depth-map discontinuities. Existing approaches either can only deal with simple cases in which the background behind the object does not change significantly, or they segment the input image into two layers. Unfortunately, such segmentation is impossible to carry out correctly for depth discontinuities formed by multiple objects, leading to visual artifacts in the generated views. Our proposed method of multilayer semitransparent-edge processing avoids these limitations and outperforms competitors in a subjective visual-quality comparison of the synthesized views.
Publication Year: 2016
Publication Date: 2016-12-01
Language: en
Type: article
Indexed In: ['crossref']
Access and Citation
Cited By Count: 1
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot