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

Light field super-resolution three-dimensional reconstruction method and system

A 3D reconstruction and super-resolution technology, applied in neural learning methods, image analysis, 3D modeling, etc., can solve problems such as microscopic imaging of dynamic samples

Pending Publication Date: 2021-12-31
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above defects or improvement needs of the prior art, the present invention provides a light field super-resolution three-dimensional reconstruction method and system, the purpose of which is to generate a super-diffraction-limited light field image that cannot be obtained by actual shooting through simulation, which is different from actual shooting The obtained light field images are paired, while maintaining the advantage of fast acquisition of 3D information in the light field, the spatial resolution breaks through the diffraction limit of the light field, thus solving the problem that the existing high-resolution 3D imaging technology cannot display dynamic samples. Technical Issues in Micro Imaging

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
  • Light field super-resolution three-dimensional reconstruction method and system
  • Light field super-resolution three-dimensional reconstruction method and system
  • Light field super-resolution three-dimensional reconstruction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0072] This embodiment provides a light field super-resolution three-dimensional reconstruction method, such as figure 1 As shown, the simulated high-resolution light field image is paired with the corresponding low-resolution light field image, and the paired high-resolution and low-resolution multi-view images are extracted, which are input into the convolutional neural network for training, and realized through network forward reasoning. Super-resolution of light field images, combined with light field 3D reconstruction network to obtain super-resolution 3D images, can perform high-resolution 3D imaging of dynamic samples. Include the following steps:

[0073] (1) Take the static sample as the target and obtain its high-resolution factual 3D data;

[0074] (2) Perform analog sampling on the high-resolution factual three-dimensional data obtained in step (1), and obtain low-resolution light field projections that match the light field imaging system hardware and high-resolu...

Embodiment 2

[0088] This embodiment provides a light field super-resolution three-dimensional reconstruction method, such as figure 1 As shown, the simulated high-resolution light field image is paired with the corresponding low-resolution light field image, and the paired high-resolution and low-resolution multi-view images are extracted, which are input into the convolutional neural network for training, and realized through network forward reasoning. Super-resolution of light field images, combined with light field 3D reconstruction network to obtain super-resolution 3D images. Include the following steps:

[0089] (1) Take the static sample as the target and obtain its high-resolution factual 3D data;

[0090] (2) Perform analog sampling on the high-resolution factual three-dimensional data obtained in step (1), and obtain low-resolution light field projections that match the light field imaging system hardware and high-resolution light field projections with target resolution;

[00...

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 discloses a light field super-resolution three-dimensional reconstruction method and system. The method comprises the following steps: (1) taking a static sample as a target, and obtaining high-resolution fact three-dimensional data of the static sample; (2) carrying out analog sampling to obtain low-resolution light field projection matched with light field imaging system hardware and high-resolution light field projection with target resolution; (3) training the super-resolution network model as training data until the model converges to obtain a light field super-resolution reconstruction model; (4) inputting light field image data obtained by a light field imaging system by taking a static or dynamic sample as a target into the light field super-resolution reconstruction model to obtain a light field image with a target resolution; and (5) performing three-dimensional reconstruction to obtain a high-resolution three-dimensional image of a static or dynamic sample. According to the invention, a light field multi-view image with an ultra-diffraction limit can be obtained at an ultra-high speed, and finally microscopic imaging of a dynamic sample, such as a submicron biological dynamic process, is realized.

Description

technical field [0001] The invention belongs to the field of biophoton microscopic imaging, and more specifically relates to a method and system for super-resolution three-dimensional reconstruction of light field. Background technique [0002] Light field microscopy imaging technology has a very high volume imaging rate. Compared with the conventional high-resolution 3D imaging technology that needs to scan and collect multiple 2D images to obtain 3D information, it only needs to collect a single image to obtain the 3D image. Information, which greatly improves the speed of three-dimensional imaging, and provides the possibility for high-speed dynamic imaging of the living body. Light field microscopy technology adds a microlens array to the detection optical path, so that the acquired two-dimensional image can contain both lateral and angular information. However, because this method needs to obtain both lateral and angular information through a single image, the lateral ...

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): G06T17/20G06T3/40G06K9/62G06N3/04G06N3/08
CPCG06T17/20G06T3/4053G06N3/04G06N3/08G06T2207/10056G06T2207/20081G06F18/253
Inventor 费鹏朱兰馨易成强
Owner HUAZHONG UNIV OF SCI & TECH
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