Method for inpainting and restoring processing of vacancy of DIBR (Depth Image Based Rendering) target image

Abstract

The invention provides a method for the inpainting and restoring processing of a vacancy of a DIBR (Depth Image Based Rendering) target image. A special vacancy inpainting and restoring mode with a plurality of times of local restoring is applied to the large vacancy taking the adjacent non-null pixel points as the background pixel points on at least one side of the left side and the right side; in each process of local restoring, priority contrast is applied to ensuring that a selected to-be-restored block has more obvious parameter characteristics on the aspects of background pixel distribution, gradient, depth distribution, and the like; and when the relevance of the RGB (Red, Green, Blue) value with the depth value of the pixel, which is measured through the matching coefficient based on an SSD (Solid State Disk) principle, is used for searching a matched block, the searching targeting is strong, the matching accuracy is high, the profile of a foreground object can be better kept, the phenomena of pseudomorphism overlapping and distortion on the edge of the foreground object can be prevented, the accurate transmission of the vacancy inpainting and restoring texture is ensured, and the restoration defects such as the dislocation, the disconnection, and the texture disorder, which are not in line with the visual psychology, between the vacancy inpainting and restoring area and a background image are greatly reduced.

Description

technical field [0001] The present invention relates to the field of 3D video technology and depth-based image rendering technology, in particular to a DIBR target image hole filling and repairing processing method. Background technique [0002] Depth-Image-Based Rendering (DIBR for short) is a method to generate new left and right viewpoint images ( That is, the target image) image processing technology. Compared with the traditional 3D video technology that needs to transmit two channels of video images for the left and right eyes, the DIBR technology only needs to transmit one channel of video and its depth image to generate a stereoscopic image pair, and can easily realize two-dimensional and three-dimensional images. Switching Because of this, DIBR technology has been widely used in the generation of 3D television stereoscopic image pairs (called stereo pairs), and it has also attracted increasing interest. [0003] In the 3D TV processing system, the original video i...

AI Technical Summary

Problems solved by technology

For example, Wu et al. used the watershed algorithm to segment the foreground and background on the depth map, but the watershed algorithm is prone to over-segmentation, and requires iteration to merge the segments, which has a high time complexity; Wang et al. Create a background library through frame difference, but this requires the use of other multi-frame color images to build a background library, which is technically difficult and not practical

Images