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

A method for cross-modal retrieval of three-dimensional model based on sketch retrieval

A 3D model, cross-modal technology, applied in the field of cross-modal retrieval, to achieve the effect of increasing distance, good accuracy, and improving retrieval precision

Active Publication Date: 2019-01-15
BEIFANG UNIV OF NATITIES
View PDF5 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Despite the advantages of convenience and easy access to the sketch-based retrieval method, it still has many thorny problems

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
  • A method for cross-modal retrieval of three-dimensional model based on sketch retrieval
  • A method for cross-modal retrieval of three-dimensional model based on sketch retrieval
  • A method for cross-modal retrieval of three-dimensional model based on sketch retrieval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described below in conjunction with specific examples.

[0039] The cross-modal retrieval method based on the sketch retrieval 3D model provided in this embodiment uses the triple network as the basic structure, trains a cross-domain classifier, continuously reduces the difference between cross-domain modalities, and improves retrieval accuracy, such as image 3 As shown, our overall network structure is shown, some weights are shared between anchor points and positive and negative examples, features are extracted through convolution, pooling and other operations, and the retrieval task is completed through the triple network. It includes the following steps:

[0040] 1) Data set selection

[0041] The data set uses the standard SHREC2013 and SHREC2014 data sets, each data set includes a subset of 3D model data and a subset of sketch data; the SHREC2013 data set contains 1258 3D models and 7200 sketches, a total of 90 categories, a...

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

ion discloses a cross-modal retrieval method based on a sketch retrieval three-dimensional model, comprising the following steps: 1) selecting a data set; 2) rendering the three-dimensional model datain the dataset, and obtaining a plurality of two-dimensional views from one three-dimensional model, wherein the two-dimensional views are used for representing the three-dimensional model, and the sketch data is uniformly sized into 256 plus 256; 3) training a sketch classifier and a view classify; 4) constructing the depth metric learning space: taking the sketch and view of the original dataset as the input of the network, taking the parameters of the sketch and view classifier as the parameters of the network, and achieving the retrieval goal through training. The invention is mediated byviews, minimizing the semantic gap between the 3D model and the sketch. A novel network structure of sketch retrieval 3D model is constructed, which achieves very good classification accuracy on SHREC2013 and SHREC2014. The experimental results fully show that our network framework can retrieve the corresponding 3D model from the sketch.

Description

technical field [0001] The invention relates to the technical field of cross-modal retrieval, in particular to a cross-modal retrieval method for retrieving three-dimensional models based on sketches. Background technique [0002] In recent years, due to the strong visual stimulation and wider application scenarios of 3D models, the data of 3D models has exploded. With the development of technologies such as 3D scanning and 3D printing, people can obtain 3D data more efficiently. In order to help users easily obtain the required 3D models, and to reuse and share the 3D models, 3D model retrieval technology has become a hot topic in computer graphics. [0003] The widespread popularity of touch-screen devices and handwriting devices, as well as the popularity of emoticons, has led people to try to use hand-drawn sketches instead of words or language for abstract expression. Through sketches, users can express their ideas more quickly and accurately, and the randomness and c...

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
IPC IPC(8): G06F16/51G06K9/62
CPCG06F18/2411
Inventor 白静王梦杰田栋文
Owner BEIFANG UNIV OF NATITIES
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com