Perceptual Loss Based Angular Super-Resolution Reconstruction Method for Light Field Images

A super-resolution reconstruction and light field image technology, which is applied in image analysis, image enhancement, image data processing, etc., can solve problems such as blurring and achieve good visual effects

Active Publication Date: 2021-08-31
长春禹诚科技技术有限责任公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The above methods estimate the model by minimizing the mean square error between the new perspective image and the target image, but the pixel-level loss is not consistent with the visual loss observed by the human eye. It is possible that the pixel-level loss is higher. more blurred than the one with the lower loss

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
  • Perceptual Loss Based Angular Super-Resolution Reconstruction Method for Light Field Images
  • Perceptual Loss Based Angular Super-Resolution Reconstruction Method for Light Field Images
  • Perceptual Loss Based Angular Super-Resolution Reconstruction Method for Light Field Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0024] Such as figure 1 As shown, the input is images of four observation angles, and the present invention generates new angle images through three different angle super-resolution models, and improves the angle resolution of light field images. The model consists of two parts, one is the light field image angle super-resolution network f W , and the second is the perceptual loss network φ, such as figure 2 .

[0025] Angular Super-Resolution Network f W is a deep residual convolutional neural network as shown in Table 1:

[0026] layer active size input layer 6×36×36 or 12×36×36 Convolutional layer 1, filter size 64×9×9 64×36×36 Residual block 1, 64 filters 64×36×36 Residual block 2, 64 filters 64×36×36 Residual block 3, 64 filters 64×36×36 Residual block 4, 64 filters 64×36×36 Ou...

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 relates to a light field image angle super-resolution reconstruction method based on perceptual loss, belonging to the field of light field imaging. This method uses the mean square error of the high-dimensional image features extracted by the pre-training model as the loss function, and learns the nonlinear mapping relationship between the observation image and the target view image by constructing a network model composed of four residual blocks, thereby reconstructing A new perspective image. By introducing the perceptual loss expressing high-dimensional features, the present invention can better maintain the texture details of the new perspective image after super-resolution reconstruction, and has better visual effects.

Description

technical field [0001] The invention belongs to the field of light field imaging, and relates to a method for super-resolution reconstruction of light field image angles based on perceptual loss. Background technique [0002] Light field imaging has become a focus in the research of next-generation imaging systems. The light field image contains the spatial information and angle information of the light, so the light field camera can capture images from multiple perspectives at one time. Several studies have shown that light field images have good application prospects in many fields, such as image saliency detection, image depth estimation, etc. The basic principle of the full light field camera is to insert a microlens array at the primary image plane of the general imaging system, and the light recorded by each microlens corresponds to the scene image at the same position and different angles of view, so as to obtain a 4-dimensional light field information, including 2 ...

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 Patents(China)
IPC IPC(8): G06T5/00
CPCG06T5/001G06T2207/10052G06T2207/20081G06T2207/20084
Inventor 秦红星王孟辉
Owner 长春禹诚科技技术有限责任公司
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