A multi-view naked-eye 3D image synthesis method based on super-resolution anti-aliasing

A naked-eye 3D and image synthesis technology, which is applied in image communication, stereo system, electrical components, etc., can solve problems such as the need to improve the clarity of the stereo image, the anti-aliasing performance to be verified, and the reduction of the image synthesis effect, so as to eliminate spectrum aliasing effect, good spectral aliasing effect, and the effect of speeding up training

CN110430419BActive Publication Date: 2021-06-04PEKING UNIV
10 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2021-06-04

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The present invention provides a multi-view naked-eye three-dimensional image synthesis method based on super-resolution anti-aliasing. The method utilizes the WDSR algorithm to optimize the image zooming process. Since the WDSR algorithm can only enlarge the image by an integer multiple, the zoomed image will be Combined with the traditional interpolation algorithm, the original image is scaled to the size of the target composite image. Then, a multi-view sub-pixel mapping table is calculated according to the multi-view sub-pixel mapping relationship of the columnar grating. Then make each viewpoint mask according to the sub-pixel mapping table, use the mask to accelerate the synthesis speed of the stereogram, and rearrange and combine a part of each viewpoint view after zooming, and finally get a stereoscopic composite image with better effect than using the traditional interpolation algorithm . The invention can reduce the sex-to-noise ratio of the stereo composite image and improve the display quality of the stereo composite image.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention provides a multi-viewpoint naked-eye three-dimensional image synthesis method based on super-resolution anti-aliasing, and specifically relates to the technical field of columnar grating multi-viewpoint naked-eye three-dimensional image synthesis.

[0002] technical background

[0003] With the rise of the big data era, the amount of information is gradually increasing, and people have higher pursuit of data visualization, data receiving speed, and information acquisition per unit time; in addition, visual information is the most important aspect of human perception of the external world. Under the promotion and influence of the era of big data, the research on the processing of visual information has great prospects and significance. As the traditional two-dimensional images can no longer meet people's needs, the three-dimensional display technology of three-dimensional information has emerged as the times require, and has received extens...

Examples

Embodiment Construction

[0044] The present invention will be further described through implementation examples below in conjunction with the accompanying drawings, but the scope of the present invention will not be limited in any way.

[0045] The block diagram of the multi-viewpoint naked-eye three-dimensional image synthesis method based on super-resolution anti-aliasing provided by the present invention is shown in the attached figure 1 shown. In the embodiment of the present invention, the method provided by the present invention specifically includes the following steps:

[0046] 1) Use the WDSR algorithm to zoom in and out of each viewpoint;

[0047] Using the DIV2K data set with 800 high-definition pictures, each picture is cut into a size of 96×96 as the real value, and the downsampled low-resolution picture is used as input. After the mapping relationship is established, the network that can achieve the output effect is trained. , to super-resolve the low-resolution image. Among them, WDS...