Image Completion for View Synthesis Using Markov Random Fields and Efficient Belief Propagation

TL;DR

This paper introduces an inpainting algorithm for view synthesis that effectively fills disocclusions using Markov random fields and belief propagation, improving image quality over existing methods.

Contribution

It presents a novel inpainting approach for disocclusion filling in view synthesis using MRFs and efficient belief propagation, outperforming prior algorithms.

Findings

Significant improvement in image quality over state-of-the-art methods

Effective handling of disocclusions in synthesized views

Demonstrated superiority through comparative experiments

Abstract

View synthesis is a process for generating novel views from a scene which has been recorded with a 3-D camera setup. It has important applications in 3-D post-production and 2-D to 3-D conversion. However, a central problem in the generation of novel views lies in the handling of disocclusions. Background content, which was occluded in the original view, may become unveiled in the synthesized view. This leads to missing information in the generated view which has to be filled in a visually plausible manner. We present an inpainting algorithm for disocclusion filling in synthesized views based on Markov random fields and efficient belief propagation. We compare the result to two state-of-the-art algorithms and demonstrate a significant improvement in image quality.