Unlock instant, AI-driven research and patent intelligence for your innovation.

Neural network training and matting method and device, and storage medium

A neural network training and neural network technology, applied in the fields of neural network training and map-cutting methods and devices, and storage media, can solve the problems of inability to obtain a good map-cutting effect, complex and changeable map-cutting objects, etc. time, the effect of improving the quality of the cutout

Pending Publication Date: 2022-07-12
SHANGHAI SENSETIME TECH DEV CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Although this method saves a lot of initial interaction time, due to the complex and changeable matting objects, when there are multiple objects in an image, it is impossible to select the correct object for matting without interactive information guidance. When it is a transparent object, it is usually impossible to get a better matting effect

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
  • Neural network training and matting method and device, and storage medium
  • Neural network training and matting method and device, and storage medium
  • Neural network training and matting method and device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. Where the following description refers to the drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as recited in the appended claims.

[0050] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "the," and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that the term "and / or" as 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
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a neural network training and matting method and device and a storage medium, and the method comprises the steps: determining a region of interest on a sample image; wherein the concerned area is an image area where an object concerned by the user is located; inputting the sample image marked with the region of interest into an initial neural network, and determining a prediction mask graph corresponding to the region of interest by the initial neural network; wherein the prediction mask graph is used for identifying foreground pixel points and / or background pixel points in the region of interest; based on the sample image marked with the region of interest and the prediction mask image, determining a prediction matting mask which is output by the initial neural network and corresponds to the region of interest; and training the initial neural network based on the difference between the predicted cutout mask and a real mask corresponding to the region of interest, and obtaining a target neural network for cutout after the training is completed.

Description

technical field [0001] The present disclosure relates to the field of computer vision, and in particular, to a neural network training and mapping method and device, and a storage medium. Background technique [0002] Image matting is a fundamental and challenging task in computer vision. Given one or more natural images, predict the foreground and background parts, and estimate the transparency value of the pixels in the mixed region. The matting technology has important research value and a wide range of application scenarios. Such as video conferencing, live scene replacement, film processing, image editing, video editing, etc. [0003] Currently, matting algorithms can be divided into two categories: [0004] The first category is Trimap-based methods. [0005] This type of method requires the user to provide an accurate three-part map of the object to be cut while giving a color mode (Red Green Blue, RGB) image input, that is, to mark a certain foreground, a certain ...

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): G06T7/11G06T7/194G06T5/50G06N3/04G06N3/08
CPCG06T7/11G06T7/194G06T5/50G06N3/08G06T2207/20081G06T2207/20084G06T2207/20221G06N3/045
Inventor 王斌杨丁豪钟华平何聪辉
Owner SHANGHAI SENSETIME TECH DEV CO LTD