A dibr virtual image restoration method suitable for high-definition 2d/3d conversion

Abstract

The invention discloses a DIBR (depth image-based rendering) virtual image restoration method applicable to high-definition 2D / 3D (two-dimensional / three-dimensional) conversion. The method comprises steps as follows: generating a general background dictionary DB; synthesizing a sparse dictionary DI: constructing a sample dictionary DS in a background area of a video frame image IF, and synthesizing the sparse dictionary DI according to the generated general background dictionary DB and the sample dictionary DS; performing void estimation and classification processing; performing filling restoration processing on each II-class void RHII. With the adoption of the method, through classification processing and sparse dictionary expression, the complexity of calculation is significantly reduced while the 3D virtual image rendering effect is improved, and the method is more applicable to processing of mass video information in high-definition 2D / 3D conversion.

Description

technical field [0001] The invention relates to the technical field of three-dimensional video, in particular to a 2D / 3D video conversion technology, in particular to a DIBR virtual image restoration method suitable for high-definition 2D / 3D conversion. Background technique [0002] At present, three-dimensional (3D) video is gradually popularized, and China Central Television (CCTV) also tried to broadcast a 3D channel on New Year's Day in 2012. 3D video has gradually become a trend of current development. However, insufficient video sources have become the main bottleneck restricting the rise of this industry. In this case, converting 2D video to 3D video is an effective way to solve this problem. [0003] There are generally two rendering methods for converting 2D video to 3D video: one is to directly reconstruct the left and right eye image pairs with parallax from a single video frame by using a certain method; the other is based on the depth map The rendering (Depth ...

AI Technical Summary

Problems solved by technology

The first method is based on partial differential equations, which is suitable for deriving and repairing holes in small areas; the second method is based on block-based texture synthesis technology to fill in lost information. This method can repair holes in large areas and has high operating efficiency, but the repair time Block matching is based on greedy search, which may cause obvious repair errors; the third is dictionary-based sparse representation theory, research results in recent years have shown that this method can achieve better repair results, but this method usually generates The dictionary needs to be iteratively optimized, and the amount of calculation is large, which cannot fully meet the conversion requirements of video 2D / 3D

[0008] Therefore, the existing DIBR-based virtual image repair method in 2D / 3D video conversion cannot effectively guarantee the conversion and synthesis of virtual images, especially the more and more popular high-definition video images, thus affecting the actual conversion effect of 3D video

Images