3D similarity judgment

We would like to introduce the 3D similarity judgment technology that we have developed for the first time in the world.

What is 3D similarity judgment?

3D similarity judgment means searching for a shape similar to the input 3D shape from the 3D shape data, and we have developed the world’s first 3D AI model that can perform 3D similarity judgment.

Conventional similarity judgment technology

As a conventional method of determining similarity, there is a method of searching for similar shapes by hand-picking character information such as part numbers using text-based AI. However, there were also problems such as the enormous amount of time and effort required to prepare the text information for searching.

In the conventional similarity judgment, even when identifying a 3D shape, a snapshot group of 2D images is used instead, and there is a problem that it becomes difficult to maintain recognition accuracy.

Many D sites such as the manufacturing industry and the construction industry are shifting to operations based on 3D shapes using 3D CAD. Computer-aided technologies such as CAD, CAM, and CAE are also based on 3D shapes. Therefore, it is indispensable for AI to handle 3D data as well.

For details on the problems of conventional AI, please refer to the activity outline.

If you can directly recognize the 3D shape like our method, you can reduce the trouble of preparation as described above and avoid the problem of shooting.

Mechanism of 3D similarity judgment

In 3D similarity judgment, shape features are extracted and compared with existing shape features in 3D shape data, so generative models such as VAE and GAN are used for training.

In the similarity judgment, the degree of deviation between the two shapes is expressed by the distance, and if they match, it will be close to 0.

Introducing products for 3D similarity judgment

We have prepared a demo site of 3D matching AI PLM equipped with a 3D similarity judgment function.

At the 3D matching AI PLM demo site, you can try out matching examples of bolts and brackets.

In 3D matching AI PLM of bolts, classification is performed by bolt head shape and similarity judgment is performed considering the size of bolt length and diameter.

In addition, in the 3D matching AI PLM of the bracket, the similarity is judged by the overall shape of the bracket.

On the demo site, you can try out an example of bolt and bracket similarity analysis. For bolts, determine the similarity by considering the head shape, bolt length, and bolt diameter size, and for brackets, considering leg length, width, plate thickness and holes, slits, and so on.