Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Depth image fusion method applicable for depth image-based rendering (DIBR) preprocessing process

A fusion method and depth map technology, applied in the field of 3D video, can solve the problems of geometric deformation, affecting the actual conversion effect of 3D video, and cannot effectively ensure the conversion and synthesis of virtual images without distortion, so as to achieve the improvement of hole repair and overcome the distortion of depth map and the effect of the oversmoothing problem

Inactive Publication Date: 2017-05-31
NANYANG NORMAL UNIV
View PDF14 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of method has high operating efficiency and obvious effect, but the smoothing filter may cause geometric deformation in the edge area of ​​the object in the virtual image (especially the edge in the vertical direction)
Therefore, in the 2D / 3D video conversion, the depth map preprocessing link in the existing DIBR technology cannot effectively guarantee the conversion and synthesis of the virtual image without distortion, thus affecting the actual conversion effect of the 3D video

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
  • Depth image fusion method applicable for depth image-based rendering (DIBR) preprocessing process
  • Depth image fusion method applicable for depth image-based rendering (DIBR) preprocessing process
  • Depth image fusion method applicable for depth image-based rendering (DIBR) preprocessing process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with accompanying drawing and embodiment:

[0036] figure 1 It shows the processing flow of the existing DIBR system. For the input original depth map, the depth map is firstly smoothed and filtered in the preprocessing link, so as to reduce the occurrence of most holes during rendering by optimizing the partial structure of the depth map; then, Using the DIBR rendering processing method, using the depth image and the calibrated camera parameters, the pixels in the reference image are mapped to the target image; finally, using the hole filling method to repair a small amount of holes left in the rendering process, and output the converted left and right eye virtual image.

[0037] Among them, DIBR rendering processing is an important step in the 2D / 3D conversion method. It describes an accurate point-to-point mapping relationship, and can use the depth information to render a virtual stereoscopic vide...

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 present invention discloses a depth image fusion method applicable for a depth image-based rendering (DIBR) preprocessing process. The method comprises the following steps of performing gradient analysis on an original depth image, and pre-estimating empty areas in a new viewpoint image; generating an initial influence distribution map according to distribution of the pre-estimated empty areas; diffusing the initial influence distribution map by using a texture image in a dimensional transformation space; and fusing, based on the diffused influence distribution map, the original depth image and a pre-smoothed depth image, and generating an optimized depth image. According to the method, in an efficient dimensional transformation space, the original depth image and the pre-smoothed depth image are fused by using the texture feature fusion-based influence distribution map, so that the smoothing strength of the optimized depth image is adjusted adaptively in different areas, the empty areas are smoothed effectively so as to eliminate the empty impact, and non-empty areas are not smoothed excessively so as to avoid extra twist.

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 image fusion 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 rendering (Depth Image...

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
IPC IPC(8): H04N13/00G06T5/00G06T5/50G06T15/20
CPCH04N13/106G06T5/50G06T15/205G06T2207/10021G06T2207/20221G06T5/70
Inventor 刘伟郑扬冰刘红钊崔明月张新刚马世榜叶铁
Owner NANYANG NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com