Three-dimensional model cross-domain retrieval method and system based on complex background image

Abstract

The invention discloses a three-dimensional model cross-domain retrieval method and system based on a complex background image. The method comprises the steps: building a data set suitable for triplenetwork input, enabling a three-dimensional model to be expressed through multiple views, and unifying the size of image data; designing a cross-domain retrieval triple deep network; adopting an imageaccurate feature extraction network and a three-dimensional model grouping view feature extraction network for completing effective feature extraction of input data, constructing a feature joint embedding space, mapping the features of different domains into the same high-dimensional space, wherein the feature distance of data of the same category is small, and the feature distance of data of different categories is large; finally, measuring the similarity between the image and the three-dimensional model in the feature joint embedding space by adopting an Euclidean distance to finish cross-domain retrieval. According to the method, the corresponding three-dimensional model can be obtained through retrieval according to the input single RGB image with complex background information.

Description

technical field [0001] The invention relates to the fields of computer graphics and computer vision, in particular to a method and system for cross-domain retrieval of three-dimensional models based on complex background images. Background technique [0002] The advent of the information age has provided a powerful boost to the development of computer hardware, and various media data such as audio, video, images, and three-dimensional data have shown a blowout growth. Today, 3D models are widely used in fields such as computer graphics and computer vision, such as 3D printing, computer-aided design, film and television animation, medical diagnosis, etc. In order to adapt to the huge and growing 3D data involved in many applications, designing fast and effective 3D model retrieval methods has become a hot issue at present. [0003] Most of the current retrieval work belongs to instance-based 3D model retrieval. This method needs to provide a 3D model to be queried, and extra...

AI Technical Summary

Problems solved by technology

[0008] The technology of the present invention solves the problem: overcomes the lack of accurate feature extraction of real images and the loss of 3D model information in the field of cross-domain retrieval of 3D models in the prior art, and provides a cross-domain retrieval of 3D models based on complex background images Method and system, design cross-domain retrieval triplet deep network construction feature joint embedding space to reduce the distribution difference of different modal data features, improve retrieval accuracy by focusing on effective feature extraction of 3D models and RGB images with complex background information, Retrieve similar 3D models based on a single RGB image

Images