3D model retrieval method and device based on convolutional neural network and multi-view image
A convolutional neural network and three-dimensional model technology, applied in the field of three-dimensional design, can solve the problem of inaccurate retrieval results and achieve the effect of fast retrieval
Inactive Publication Date: 2021-08-06
HUBEI UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, relying on manual subjective judgment, the models in the same annotation may vary greatly, and there are deficiencies such as inaccurate retrieval results.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.
[0027] It can be understood that the terms "first", "second" and the like used in this application may be used to describe various elements herein, but these elements are not limited by these terms. These terms are only used to distinguish one element from another element. For example, a first client could be termed a second client, and, similarly, a second client could be termed a first client, without departing from the scope of the present application. Both the first client and the second client are clients, but they are not the same client.
[0028] Such as figure 1 As shown, the em...
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
Login to View More Abstract
The embodiment of the present application relates to a three-dimensional model retrieval method, device, electronic equipment and storage medium based on convolutional neural network and multi-view images. Corresponding to different perspectives respectively; extracting the convolution feature of each perspective diagram through a convolutional neural network; obtaining the image entropy of each perspective diagram, and determining the convolution of each perspective diagram according to the image entropy Confidence corresponding to the feature; determine the similarity between the non-rigid three-dimensional model and each solid model in the three-dimensional model according to the convolution features of the multiple perspective images and the corresponding confidence; Solid model for rigid 3D model matching. The above-mentioned three-dimensional model retrieval method, device, electronic device and storage medium based on the convolutional neural network and the multi-view image can retrieve the three-dimensional model more accurately.
Description
technical field [0001] This application relates to the field of 3D design, in particular to a 3D model retrieval method, device, electronic equipment and storage medium based on convolutional neural network and multi-view images. Background technique [0002] Compared with various media data such as images, videos, and sounds, 3D models and the 3D scenes composed of them can more comprehensively and truly display objective object information, which is in line with the perception form of the human visual system, so it is widely used in product design, virtual reality, etc. , film and television animation and other fields. Quickly and accurately retrieving similar models from the model library can not only reduce the task of building repeated models, but also facilitate the management and use of 3D model materials, making 3D design easier and faster. In the current model library construction, 3D model retrieval mostly adopts a text-based retrieval method, which requires manua...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/583G06K9/62G06N3/04G06N3/08
CPCG06F16/583G06N3/08G06N3/045G06F18/22G06F18/24
Inventor 胡书山朱天放
Owner HUBEI UNIV