Depth image robust smoothing filtering method suitable for DIBR (Depth Image-based Rendering) preprocessing process

Abstract

The invention discloses a depth image robust smoothing filtering method suitable for a DIBR (Depth Image-based Rendering) preprocessing process. The method comprises the following steps that: independently carrying out edge detection on an original depth image and a texture image, carrying out consistency analysis, and generating a consistency distribution image; and under a dimension transform domain, carrying out associated filtering which combines consistency distribution with texture features on the original depth image, and generating a smoothed depth image. Under the efficient dimension transform domain, through the consistency distribution between the depth image and the texture image, the generalized associated filtering is realized, the adaptive diffusion correction of an incomplete depth image area is realized while filtering is realized, and a specific pre-correction link before a traditional filtering process is avoided so as to realize the depth image robust smoothing filtering in the DIBR preprocessing process.

Description

technical field [0001] The invention belongs to the technical field of three-dimensional video, and specifically relates to a 2D / 3D video conversion technology, in particular to a depth map robust smoothing filtering method suitable for a DIBR preprocessing process. 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 rend...

AI Technical Summary

Problems solved by technology

[0005] However, in 2D / 3D video conversion, the depth map is usually estimated and synthesized by using one or more clues in the 2D video through an algorithm, and it is difficult to guarantee the integrity and accuracy of the synthesized depth map.

In particular, the fully automatic algorithm, which has become more and more popular in recent years, directly performs efficient conversion for massive videos. Since there is no manual correction, the incomplete depth map area affects the quality of the 3D video effect rendered by the DIBR system.

Images