Online marking method for three-dimensional model component

Abstract

The invention discloses an online marking method for a three-dimensional model component. The method includes the following steps that preprocessing is conducted, and features and over-segmentation pieces of triangular patches are obtained; initial marking is conducted, a segmentation model is initialized, seed area marking is conducted on an initial three-dimensional model which is input by a user, a seed marking set is obtained, online learning is conducted on the seed marking set, and the partition model is learned; online marking is conducted, the segmentation model is used for conducting segmentation marking on an input three-dimensional model of the same type, a middle marking result is obtained, whether the result is approved or not is judged by the user, if yes, the process is over, and the middle marking result is a final marking result, and if not, the user conducts area correction on the middle marking result, the seed marking set is obtained, online learning is conducted on the seed marking set, the segmentation model is updated, the updated segmentation model is used for conducting segmentation marking on the three-dimensional model, the middle marking result is obtained, continuous iteration is conducted until the middle marking result is approved by the user, and the final three-dimensional model marking result is obtained.

Description

technical field [0001] The invention relates to a processing method for shape analysis, which belongs to the technical field of computer graphics, in particular to an online marking method for three-dimensional model components. Background technique [0002] Segmenting a 3D model and obtaining the annotations of its components is the basis for shape understanding and processing. Many tasks in the fields of geometric modeling, manufacturing, 3D model animation, and texture rely on component segmentation, and many of these problems require further analysis of segmentation. Parts are annotated, that is, identified as an instance of a known part type. However, in most cases of these applications at present, the segmentation and labeling of the input 3D model are carried out by manual definition. For example, in the application of human mesh texture synthesis, it is necessary to manually identify the part with "arm" texture or the part with "leg" texture in the mesh; in addition...

AI Technical Summary

Problems solved by technology

[0007] In short, there are three problems in the current 3D model segmentation method based on the model set. First, before segmenting and labeling the 3D model, the existing methods need to collect a large number of 3D models for training in order to obtain satisfactory labeling results; Second, the existing methods lack an efficient update mechanism. When a small number of new models are added to the existing 3D model set, all 3D models need to be retrained; thirdly, the segmentation mode is difficult to express the user's annotation intention

Images