Hole filling method for converting 2D video into 3D video

A filling method and cavity technology, which is applied in image communication, stereo system, electrical components, etc., can solve time-consuming and labor-intensive image quality, unsatisfactory and other problems, and achieve the effect of ensuring the quality of cavity filling and improving visual consistency

Pending Publication Date: 2022-06-28
北京华录新媒信息技术有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a hole filling method for converting 2D video to 3D video, so as to solve the problem of time-consuming and laborious hole filling method and unsatisfactory image quality in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Hole filling method for converting 2D video into 3D video
  • Hole filling method for converting 2D video into 3D video
  • Hole filling method for converting 2D video into 3D video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0016] like figure 1 As shown, this embodiment provides a hole filling method for converting 2D video to 3D video, including:

[0017] S1: Input the virtual viewpoint with holes and the corresponding depth map and other information, output the virtual viewpoint image after filling the holes, and judge whether the holes are processed.

[0018] S2: When the void is not processed, the boundary point of the void area is extracted. After traversing all the void points, a set of boundary points in the void region is obtained.

[0019] S3: Traverse the information source image and extract matching blocks.

[0020] S4: Calculate the matching cost between the target block of the hollow color image and the depth image at the center point and the block to be matched in the source image.

[0021] S5: Obtain the center point of the optimal matching block, and update the hole image by its neighbor block source image and depth image point.

[0022] Further, S1 includes:

[0023] S11: Du...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a hole filling method for converting a 2D video into a 3D video, and the method comprises the following steps: S1, inputting a virtual viewpoint containing a hole, a corresponding depth map and other information, outputting a virtual viewpoint image after the hole is filled, and judging whether the hole is processed or not; s2, extracting boundary points of a cavity region when the cavity is not processed; and traversing all cavity points to obtain a cavity region boundary point set. S3, traversing an information source image, and extracting a matching block; and S4, calculating the matching cost of the cavity color image and the depth image target block of the central point and the to-be-matched block of the source image. And S5, obtaining an optimal matching block center point, and updating the void image through the neighborhood block source image and the depth image point of the optimal matching block center point. Through the steps, the hole filling quality can be effectively ensured, the visual consistency of virtual viewpoint synthesis is improved, and the result is enabled to be as real as possible to be close to an original image.

Description

technical field [0001] The invention relates to a hole filling method, in particular to a hole filling method for converting 2D video to 3D video. Background technique [0002] One of the most important aspects of 2D-3D video conversion is hole filling. How to fill the generated holes is a crucial and difficult problem in the 3D video conversion technology based on disparity map. According to the different processing stages, the methods of eliminating holes can be divided into two categories: pre-processing algorithms and post-processing algorithms. Among them, the pre-processing algorithm refers to the pre-processing of the depth image before the creation of the left and right views, so as to reduce the number of generated holes. It has been introduced before, although this processing process can effectively reduce the holes. area, but it will produce distortion, which will cause geometric distortion of the shape of the object, and ultimately reduce the image quality; po...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): H04N13/261H04N13/122
CPCH04N13/261H04N13/122
Inventor 张现丰刘海军王璇章庄庄聂耳钱炫羲张雄飞
Owner 北京华录新媒信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap