Virtual viewpoint synthesis method with spatiotemporal continuity
A technology of virtual viewpoint and synthesis method, applied in the field of virtual viewpoint synthesis, can solve the problems of time discontinuity of virtual viewpoint image sequence, affect the quality of image rendering, and affect the viewing experience of users, so as to improve the rendering quality, improve the rendering quality, reduce the flickering effect
Inactive Publication Date: 2018-11-16
SOUTHEAST UNIV
View PDF5 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Since the color map and depth map of the viewpoint image are not completely corresponding to the edge of the foreground object, that is, the transition area where the depth value changes suddenly, and at the same time, the lighting environment conditions of the reference viewpoint are different in different positions, so that "artifacts" will appear in the generated virtual viewpoint image. area, which greatly affects the user's viewing experience
[0006] (2) Due to the inevitable occlusion relationship between objects, part of the background information occluded by the foreground under the original reference viewpoint is exposed to other virtual viewpoints, and a large hole is formed on the virtual viewpoint image due to the lack of occluded information, which is very Affects the drawing quality of the image
[0007] (3) Since most of the current DIBR technology solutions are limited to processing single-frame images, ignoring the correlation between frames in the image sequence, so in addition to the above-mentioned problems of holes and "artifacts", the generated virtual Viewpoint image sequences also have time discontinuities, reflected in frequent flickering
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings.
[0029] Such as figure 1 As shown, the virtual viewpoint synthesis method of the present invention comprises the following steps:
[0030] (1) First, preprocess the depth map sequences in the left and right reference viewpoint image sequences. It should be noted that the left and right reference view image sequences mentioned in the present invention include the depth map sequences and texture image sequences of the left and right reference views. The preprocessing here includes: (a) Starting from the depth map of the first frame, the depth difference between two pixels in the depth map of adjacent frames is compared with the preset threshold, so that the depth value of the pixel satisfying the threshold range is taken as The average value of the depth values of two pixels, and then continue to process the depth map of the next frame until the end of the p...
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
Login to view more Abstract
The invention provides a virtual viewpoint synthesis method with spatiotemporal continuity. The method makes full use of correlation between adjacent frames in a reference viewpoint image sequence, aglobal static background map sequence of a scene is extracted from the reference viewpoint image sequence, and based on the global background map sequence, artifact elimination and hole filling are carried out on a virtual viewpoint image sequence synthesized by a left and a right reference viewpoint image sequence. Artifact and hole problems on a virtual viewpoint image can be well solved, the quality of a single frame of virtual viewpoint image is greatly improved, and the spatiotemporal continuity of the virtual viewpoint image is also well maintained.
Description
technical field [0001] The invention relates to a method for synthesizing virtual viewpoints, in particular to a method for synthesizing virtual viewpoints with temporal and spatial continuity. Background technique [0002] With the rapid development of the 3D industry, people are no longer satisfied with the experience of 2D scenes, but more and more pursue the immersive enjoyment of being in 3D scenes. Driven by the market and technology, TV technology is also undergoing major changes, gradually transitioning from traditional TV with single function and single color to smart TV with high resolution and multimedia functions, and then to traditional 3D TV (3DTV). Ushered in Free Viewpoint TV (FTV), which is in the development momentum, and every change brings users a better viewing experience. [0003] Free viewpoint video is generated based on the virtual viewpoint rendering framework of video plus depth (V+D). Due to the limitation of video transmission bandwidth, virtual...
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
Login to view more Patent Type & Authority Applications(China)
IPC IPC(8): H04N13/117H04N13/279
Inventor 姚莉李小敏吴含前
Owner SOUTHEAST UNIV
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
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