Semi-automatic 2D to 3D method with fault tolerance

A fault-tolerant, semi-automatic technology, applied in the 3D video field, which can solve the problems of deteriorating depth map estimation quality, not fully considering the difference between texture image and depth map, and poor edge quality of depth map objects.

Inactive Publication Date: 2018-12-07
NINGBO UNIVERSITY OF TECHNOLOGY
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] (1) The difference in structure between the texture image and the depth map is not fully considered, so that the edge quality of the estimated depth map object is poor, resulting in holes and artifact damage in the subsequent virtual viewpoint image drawn based on the depth map
[0008] (2) The fault tolerance of the 2D to 3D system is not considered, and the slight misoperation of the user will seriously deteriorate the quality of the depth map estimation

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
  • Semi-automatic 2D to 3D method with fault tolerance
  • Semi-automatic 2D to 3D method with fault tolerance
  • Semi-automatic 2D to 3D method with fault tolerance

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The existing semi-automatic 2D to 3D methods all implicitly assume that the discontinuous transition of the depth map corresponds to the geometric boundary of the texture image. However, there is no necessary correspondence between the geometric structure of the depth map and the texture image. If the difference between the two is not considered, depth penetration and texture copy damage will be introduced. Considering that the influence function of the re-declining M estimator increases to a certain value, it will decline again, and the re-declining M estimator is used as the measure of structural difference. When the structural difference between the texture image and the depth map is larger than a certain threshold, the metric obtained by the re-descent M estimator starts to decrease, thus allowing to estimate the structural difference between the depth map and the texture image, effectively suppressing depth penetration and texture copying damage.

[0023] (2) Res...

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

A semi-automatic 2D to 3D method with fault tolerance comprises the following steps: key frame extraction, user annotation, annotation extraction and depth conversion, super pixel segmentation, planefitting, representative pixel extraction, structural difference description, fault tolerance mechanism, energy function construction with fault-tolerant structure correlation, generalized iterative re-weighted least squares method and depth map-based drawing. The method has the following beneficial effects: a deep propagation energy model related to a fault-tolerant structure is established by means of robust estimation, and local and global constraint relationships are combined, so that the prior knowledge of a scenario can be utilized more effectively, and the quality of the estimated depthmap is enhanced while the user annotation difficulty in semi-automatic 2D to 3D conversion is reduced.

Description

technical field [0001] The invention belongs to the field of 3D video, and in particular relates to a semi-automatic 2D to 3D conversion method with fault tolerance. Background technique [0002] With the rise of 3D video, the problems of complex production, high cost and slow update of 3D content have become increasingly prominent. Most of the current image resources are mainly 2D. 2D to 3D technology can quickly convert existing 2D images into 3D images, which plays a vital role in the development of 3D video. Semi-automatic 2D to 3D conversion can obtain accurate depth maps with a small amount of manual intervention, so it has become a current research hotspot. [0003] Semi-automatic 2D to 3D conversion is a typical ill-posed problem, and its core lies in the restoration of depth information of video images. Existing methods assume that pixels with similar colors have similar depth values ​​for sparse depth interpolation. When this assumption does not hold, depth pen...

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): H04N13/261
Inventor 安鹏袁红星郑悠
Owner NINGBO UNIVERSITY OF TECHNOLOGY
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